2026-112026-102026-092026-082026-072026-062026-05dispatchesabout

2026-10 · 1506 records

date	id	title	authors	venue	↑
2026-10-31	W7213594818	Voltage–Current-Emission Framework of Time-Resolved Electroluminescence	Hui Bao et al.	Nano Letters
2026-10-31	W7224737457	X-ray Crystallography of a Nanobody/JAM-1 Complex Informs Barrier Weakening and Enhanced Drug Permeability in a Cellular Blood–Brain Barrier Model	Liyu Chen et al.	ACS Nano
2026-10-30	2610.29927	Your Benchmark Is an Empirical Measure Over Difficulty	Yifan Sun et al.	arXiv	18
2026-10-30	2610.38331	Multi-Token Prediction Done Right	Jayden Teoh	arXiv	15
2026-10-30	2610.38352	WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video	Chenyu Mu et al.	arXiv	15
2026-10-30	2610.38425	IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation	Shaohan Yu et al.	arXiv	14
2026-10-30	2610.21143	CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models	Yingzhuo Deng et al.	arXiv	12
2026-10-30	2610.37786	WebAnything: From the Wild Web to Scalable Agent Environments	Tianci Xie et al.	arXiv	12
2026-10-30	2610.38342	Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?	Huangfei Jiang et al.	arXiv	11
2026-10-30	2610.40454	Glance: The Generator Is Its Own Reranker	Adilet Metinov et al.	arXiv	11
2026-10-30	2610.38678	AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding	Lu Wang et al.	arXiv	10
2026-10-30	2610.39664	EditAgent: Rethinking Agentic Image Editing	Haiyang Xu et al.	arXiv	10
2026-10-30	2610.39264	Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps	Peitong Duan et al.	arXiv	9
2026-10-30	2610.40564	Training Foundation Models with a Single Algorithm	Yuda Song et al.	arXiv	8
2026-10-30	2610.40453	PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions	Yue Gong et al.	arXiv	8
2026-10-30	2610.40362	Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training	Qifan Yu et al.	arXiv	7
2026-10-30	2610.39287	OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation	Junli Liu et al.	arXiv	6
2026-10-30	2610.38174	Scaling Lean Theorem Proving for Real-World Code Verification	Debargha Ganguly et al.	arXiv	5
2026-10-30	2610.39663	AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers	Bin Xu et al.	arXiv	5
2026-10-30	2609.05881	Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them	Aditi Patodiya	arXiv	4
2026-10-30	2610.36420	SO-101 Bench: Accessible Spatial Manipulation	Truman Hickok	arXiv	4
2026-10-30	2610.34298	Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents	Zhenning Shi et al.	arXiv	3
2026-10-30	2610.23656	ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics	Xiaohang Yu et al.	arXiv	3
2026-10-30	2610.25276	Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion	Yushi Lan et al.	arXiv	3
2026-10-30	2610.38293	EPSBench: Benchmarking LLM Agents for Earnings Forecasting	Yanbin Yin et al.	arXiv	2
2026-10-30	2610.38681	Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models	Yecheng Wu et al.	arXiv	2
2026-10-30	2610.39293	Unlocking Any-Order Generation in Pretrained Autoregressive Image Models	Rishav Pramanik et al.	arXiv	2
2026-10-30	2610.37695	After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System	Bo Zou et al.	arXiv	2
2026-10-30	2610.39423	FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss	Hina Otake et al.	arXiv	1
2026-10-30	W7224744201	Causal discovery and inference in COVID-19: A multiscale longitudinal analysis using mixtures of DAGs	Kosar Abdollahi et al.	PLoS ONE
2026-10-30	W7221179570	A symmetry breaking swarm optimizer derived from the Landau theory of phase transitions	Keyin Chen et al.	Scientific Reports
2026-10-30	W7223204242	An interpretable deep learning method for early hepatocellular carcinoma diagnosis on multiphase CT	Emma Sarfati et al.	Scientific Reports
2026-10-30	W7224481444	GLTF-FEDformer: an adaptive time-frequency fusion method for multivariate time series anomaly detection enhanced by prediction error embedding	Hanbing Nie et al.	Scientific Reports
2026-10-30	W7224836018	GeoCTGAN generates privacy-aware geosynthetic event data	Abu Yousuf Md Abdullah et al.	Scientific Reports
2026-10-30	W7131891388	Copy-cup gates in tensor products of group algebra codes	Ryan Tiew et al.	Physical Review A
2026-10-30	W7162118427	Quantum purity amplification for arbitrary eigenstates and multiple outputs	Zhaoyi Li et al.	Physical Review A
2026-10-30	W4406231517	HypeRL: Hypernetwork-based reinforcement learning for control of parametrized dynamical systems	Nicolò Botteghi et al.	Computer Methods in Applied Mechanics and Engineering
2026-10-30	W7224803771	BigpictureQC: multi-stain, multi-species artifact segmentation for whole-slide quality control	Marina D'Amato et al.	BMC Medicine
2026-10-30	W7224805465	Algebraic structures of the Lindblad equation	Leonel De La Cruz Bixano et al.	New Journal of Physics
2026-10-30	W7224757932	DHR-OD: Dynamic Heterogeneous Redundancy for Robust Object Detection	Fengrui Tian et al.	Applied Sciences
2026-10-30	W7224781355	A Semi-Parallel Multi-Timescale Reinforcement Learning Method for Coordinated Motion Planning and Hydraulic Control of Mobile Manipulators	Feihong Liu et al.	Applied Sciences
2026-10-30	W7224786985	Dataset Explanation Signatures for Visual Recognition: A Model-Free Region-Level Reference for Shortcut and Label-Quality Auditing	Shakhnoza Muksimova et al.	Applied Sciences
2026-10-30	W7224796159	DOD: Double Online Distillation for Continual Learning	Qiang Wang et al.	Applied Sciences
2026-10-30	W7224853653	A hybrid car-following behavior prediction framework for snowy weather based on stacking ensemble learning	Zengjie Luo et al.	PLoS ONE
2026-10-30	W7224830066	Latent-aligned scalable interpolant transformer for controllable chest X-ray synthesis	Isabella Schlattner et al.	Scientific Reports
2026-10-30	W7224943923	One-minute frequency disturbances from unintended synchronization in cyber–physical power systems	Carlos R. P. Hartmann et al.	Nature Energy
2026-10-30	W7224742153	Multiuser Two-Dimensional Display Field Communication Using Orthogonal Frequency Subband Partitioning	Pankaj Singh et al.	Sensors
2026-10-30	W7224749438	EDCS-YOLOv8: A Lightweight YOLOv8n Variant for Ship Detection in Optical Imagery	Junxi Qiang et al.	Sensors
2026-10-30	W7224784668	A Review of Fault Diagnosis Technology for Rotating Machinery Based on Deep Generative Models	Guoqiang Pang et al.	Sensors
2026-10-30	W7224853189	Lightweight Fault Identification of Magnetic Latching Needle Selectors Based on Multistage Transient Drive Current Responses	Laihu Peng et al.	Sensors
2026-10-30	W7224867589	Information-Driven Cooperative Path Planning for Multi-UAV Bearings-Only Tracking of Clustered Targets	Fuchao Xie et al.	Sensors
2026-10-30	W7224871004	Hierarchical Discriminative Feature Refinement for Robust and Lightweight Clothing Detection	Huawen Li et al.	Sensors
2026-10-30	W7224734487	A Parameter-Compact Network with Hierarchical Detail Enhancement and High-Resolution Multiscale Fusion for Small Object Detection in UAV Imagery	Jiaqi Li et al.	Remote Sensing
2026-10-30	W7224740315	Bidirectional Global-Edge Refinement Network for Aerial Infrared Segmentation in Automated Industrial Inspection	Bo Wang et al.	Remote Sensing
2026-10-30	W7224775840	Generative structure-guided denoising diffusion probabilistic model for MR to CT image synthesis in radiotherapy planning	Redha Touati et al.	Physics in Medicine and Biology
2026-10-30	W7224814814	Artificial intelligence-enabled detection of vascular perfusion defects on ventilation/perfusion (V/Q) scintigraphy for pulmonary embolism	Amir Jabbarpour et al.	Physics in Medicine and Biology
2026-10-30	W7224824287	Mark A. Ratner (1942–2026): Founded molecular electronics while spearheading the growth of science at Northwestern University	Gemma C. Solomon et al.	Proceedings of the National Academy of Sciences
2026-10-30	W7117307079	Evidence for clean d-wave superconductivity in the samarium nickelates	Qingming Huang et al.	Physical Review Letters
2026-10-30	W7224827137	Kirigami‐Inspired Stretchable Silicon Solar Cell Modules as Portable Power Sources	Yusheng Zhang et al.	Advanced Materials
2026-10-30	W7224804756	Memristive crossbar architecture for programmable and scalable terahertz metasurface	Hangbing Guo et al.	Nature Communications
2026-10-30	W7224827701	The Elusive [B(ReO 4 ) 4 ] − Anion in the Non‐Centrosymmetric Crystal Structure of K[B(ReO 4 ) 4 ]	Stefan Sutorius et al.	Angewandte Chemie International Edition
2026-10-30	W7224806679	Long-term electricity load forecasting model based on multi-period and multi-scale analysis	Xiaolin Zhang et al.	PLoS ONE
2026-10-30	W7224766628	Heteroengineering‐Induced Electronic Reconstruction for Ammonium‐Ion Energy Storage	Ji‐Chi Liu et al.	Advanced Functional Materials
2026-10-30	W7224925127	Intruding delta waves during REM sleep are associated with tau, amyloid, and forgetting in aging	Tenzin Desel et al.	Nature Communications
2026-10-30	W7224843773	BitterBuster: A virtual world for understanding naturalistic patch foraging	John P. Kasarda et al.	PLoS ONE
2026-10-30	W7224914178	A self-supervised reconstruction framework for segment-level detection of task-induced deviations in multi-channel EEG	Lucas A. Saavedra et al.	PLoS ONE
2026-10-30	W7153517455	Electrophysiological properties of mesodiencephalic junction neurons projecting to the inferior olive	Stijn Voerman et al.	The Journal of Physiology
2026-10-30	W7224774922	Conservation of a synaptic blueprint across the animal kingdom	Aiden Houcek et al.	The Journal of Physiology
2026-10-30	W7224782235	Establishing a normative model for turbulence dynamics in the brain	Jolene K. Berg et al.	Scientific Reports
2026-10-30	W7224788819	Transformer language models reveal distinct patterns in aphasia subtypes and longitudinal change	S. Saeed Ahmadi et al.	Scientific Reports
2026-10-30	W7224923331	Eye-state-dependent reorganization of EEG microstates in a pediatric transdiagnostic cohort	Ou Xu et al.	Scientific Reports
2026-10-30	W7224816718	Editing the Embryonic Brain: How In Utero Electroporation Reveals the Secrets of Cortical Development	A.A. Ermoshina et al.	International Journal of Molecular Sciences
2026-10-30	W7153222183	Mechanism of catalytic regulation by an allosteric hot spot in dihydrofolate reductase	Paul Guénon et al.	Proceedings of the National Academy of Sciences
2026-10-30	W7224748113	Deep mutational scanning of the GPCR rhodopsin reveals pleiotropic mutational effects and their roles in modulating receptor signaling	Steven K Chen et al.	Proceedings of the National Academy of Sciences
2026-10-30	W7212133376	dictyBase 2026: a reimplementation of the Dictyostelium model organism database on minimal infrastructure	Maddox Mendieta et al.	Nucleic Acids Research
2026-10-30	W7224747635	ARIEL: an openly accessible database of experimental RNA–ligand binding affinities paired with 3D structures	Mahmoud Omar Rasheed Zeyadah et al.	Nucleic Acids Research
2026-10-30	W7155029603	Near‐Infrared Imaging of H 2 O 2 in Plants With Nanosensors Under Environmentally Changing Conditions	Jiaqi Li et al.	Advanced Materials
2026-10-30	W7224768409	Synthetic tools to redirect the ubiquitin E3 ligase activity of a plant-specific N-recognin	Keely E.A. Oldham et al.	Nature Communications
2026-10-30	W7155156745	System size dependence of collisionless reconnection rate	Yi-Min Huang et al.	Physical Review Letters
2026-10-30	W7202139944	A Search for GeV Emission from Magnetar Giant Flare Candidates with Fermi-LAT	Vikas Chand et al.	The Astrophysical Journal
2026-10-30	W7213890908	Tidal Dissipation from Circularization in Kepler Binaries	Joshua A Schussler et al.	The Astrophysical Journal
2026-10-30	W7214388495	Stellar Collisions from Self-consistent Stellar Dynamics around Growing Supermassive Black Holes	Fupeng Zhang et al.	The Astrophysical Journal
2026-10-30	W7215736994	Eight Gamma-Ray Bursts Observed with the Fermi Gamma-Ray Burst Monitor: Significant Quasi-thermal Components and Conditional Jet Constraints	Zilong Du et al.	The Astrophysical Journal
2026-10-30	W7223130564	Coevolution of Dust Growth and Gravitational Instability in Massive Protostellar Disks	Ryota Yamamuro et al.	The Astrophysical Journal
2026-10-30	W7224750142	Solar Orbiter’s Far-side Magnetogram Impacts on Coronal Holes and Solar Wind Predictions	Evangelia Samara et al.	The Astrophysical Journal
2026-10-30	W7224791324	Planetary Accretion Is Less Frequent in Wide Binaries: Evidence from Metal-enriched White Dwarfs in DESI DR1	Siyi Xu et al.	The Astrophysical Journal
2026-10-30	W7224881884	Perpendicular Heating of Solar Wind Protons Driven by Proton Cyclotron Waves Upstream of Mars	Xiaotong Yun et al.	The Astrophysical Journal
2026-10-30	W7224892301	An Exploration of In-band Spectral Index Techniques for Extended Radio Sources with EMU	Brianna D. Ball et al.	The Astrophysical Journal
2026-10-30	W7224927107	A New Framework for Modeling Solar Flares from Magnetohydrodynamic to Kinetic Processes	Joel C. Allred et al.	The Astrophysical Journal
2026-10-30	W7224944545	Damping and Dispersion of Acoustic Waves in the Solar Corona	Badma Borisovich Mikhalyaev et al.	The Astrophysical Journal
2026-10-30	W7130561082	Narrative theory-driven LLM methods for automatic story generation and understanding: a survey	David Y. Liu et al.	Artificial Intelligence Review
2026-10-29	2610.39302	Proving and Improving the Platonic Representation Hypothesis with JEPAs	Randall Balestriero et al.	arXiv	60
2026-10-29	2610.40614	L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory	Jinhyeok Choi et al.	arXiv	39
2026-10-29	2610.40647	Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers	Jiongfan Yang et al.	arXiv	24
2026-10-29	2610.40599	HairDeck: Animation-Ready Stylized Hair Cards from a Single Image	Yuze He et al.	arXiv	23
2026-10-29	2610.22507	RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents	Yunqi Liu et al.	arXiv	18
2026-10-29	2610.39633	Intrinsic Distribution Matching	Deyuan Liu et al.	arXiv	18
2026-10-29	2610.22990	PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas	Haoming Li et al.	arXiv	17
2026-10-29	2610.39301	Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities	Yunhang Shen et al.	arXiv	13
2026-10-29	2610.30161	TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents	Krishanu Adhikary et al.	arXiv	10
2026-10-29	2610.20832	Amortizing Sequential Experimental Design in Reasoning LLMs	Anita Kriz et al.	arXiv	9
2026-10-29	2610.30132	LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data	Zhennan Wan et al.	arXiv	8
2026-10-29	2610.35671	Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks	Yao Huang et al.	arXiv	7
2026-10-29	2610.33645	PreView: Enhancing GUI Grounding with Preprocessed Views and Cues	Wenjun Hou et al.	arXiv	4
2026-10-29	2610.27100	LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models	George Nigmatulin et al.	arXiv	4
2026-10-29	2610.36095	Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load	Hennadii Kutomanov	arXiv	4
2026-10-29	2610.29702	CausGround: Causal Interaction Grounding for Adaptive Embodied Planning	Yijun Shen et al.	arXiv	4
2026-10-29	2610.37626	Know, then Draw: A New Learning Paradigm for Visual Generation	Yucheng Mao et al.	arXiv	2
2026-10-29	W4406975366	Chiral altermagnon in MnTe	Daniel Jost et al.	Science
2026-10-29	W7224525382	Stimulated protein degradation to promote mitochondrial function and neuronal survival	Srividya Chandrasekhar et al.	Science
2026-10-29	W4417000365	Dynamo and Jet Interconnections in GRMHD Simulations of Black Hole Accretion Disks	P. S. Santhiya et al.	The Astrophysical Journal
2026-10-28	2610.38568	A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement	Yu Liu et al.	arXiv	62
2026-10-28	2610.35962	h1: A Taste of the Bitter Lesson in Automated Theorem Proving	Skander Moalla et al.	arXiv	19
2026-10-28	2610.35724	MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting	Shuyun Wang et al.	arXiv	19
2026-10-28	2610.37386	Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data	Geunhyoung Kim et al.	arXiv	17
2026-10-28	2610.37649	Can LLMs Uncover Hidden Physical Laws through Free Exploration?	Zhen Yang et al.	arXiv	16
2026-10-28	2610.26185	MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching	Yitong Li et al.	arXiv	15
2026-10-28	2610.35439	Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams	Yinsong Yan et al.	arXiv	15
2026-10-28	2610.37585	Timestral	Adrien Petralia et al.	arXiv	13
2026-10-28	2602.10657	The Lexical Imprint of Pre-training Data	Jeonghoon Kim et al.	arXiv	12
2026-10-28	2610.36791	RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions	Haoyu Zhao et al.	arXiv	11
2026-10-28	2610.34674	Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation	Hyunwoong Bae et al.	arXiv	11
2026-10-28	2610.34714	SearchHorizonBench: A Benchmark for Search Value in AI Agents	Jingjie Ning et al.	arXiv	11
2026-10-28	2610.29003	T-DIG: Text-Conditioned Diversity for Image Generation	Simran Khanuja et al.	arXiv	8
2026-10-28	2610.37624	Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions	Anouar Imel et al.	arXiv	8
2026-10-28	2610.37255	Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces	Jian Mu et al.	arXiv	8
2026-10-28	2610.37175	MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model	Brian Ko et al.	arXiv	8
2026-10-28	2610.30435	Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models	Taewhoo Lee et al.	arXiv	7
2026-10-28	2610.36192	Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models	Ziqiao Wang et al.	arXiv	6
2026-10-28	2610.34894	What Outcome RL Buys: Finishing, Reliability, Rarely Reach	Shan Yang	arXiv	6
2026-10-28	2610.26030	Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation	Xuyuan Xiong et al.	arXiv	6
2026-10-28	2610.37219	Vision-Language-Action or World-Action? Just Action Models	Yonghao Yu et al.	arXiv	6
2026-10-28	2610.36022	Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding	Rui Yang et al.	arXiv	6
2026-10-28	2610.33066	OvisOCR3 Technical Report	Yu Xia et al.	arXiv	6
2026-10-28	2610.22684	AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents	Liqin Ye et al.	arXiv	5
2026-10-28	2610.36082	How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning	Johnny Yu et al.	arXiv	5
2026-10-28	2610.31924	Sub-monolayer tracking of molecular states at buried interfaces	Harlan Heilman et al.	arXiv	4
2026-10-28	2610.34921	PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds	Jinyuan Hu et al.	arXiv	4
2026-10-28	2610.33245	AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science	Atharva Naik et al.	arXiv	3
2026-10-28	2509.05512	Quaternion Approximate Networks for Enhanced Image Classification and Oriented Object Detection	Bryce Grant et al.	arXiv	2
2026-10-28	2610.36184	Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It	Sanjid Hasan et al.	arXiv	1
2026-10-28	W7224107502	Emotion regulation capacity lacks a shared neural signature	Maurizio Sicorello et al.	Nature
2026-10-28	W7224084810	Genetic variants shape single-cell chromatin accessibility and disease risk	Angli Xue et al.	Nature
2026-10-28	W7224109065	Rare and common genetic variants shape single-cell immune gene expression	Anna S. E. Cuomo et al.	Nature
2026-10-28	W7224097778	MCT1-dependent mitochondrial lactate import sustains cardiac metabolism	Ahmad A. Cluntun et al.	Nature
2026-10-28	W7224119658	Perinatal elimination of genetically aberrant human cortical neurons	Diane D. Shao et al.	Nature
2026-10-28	W7224129972	SWI/SNF complexes shape 3D chromatin architecture through CTCF and cohesin	Sonia M. Debek et al.	Nature
2026-10-28	W7139913235	Lensing in the Blue. III. Weak-lensing Shape Catalogs of 30 Merging Galaxy Clusters	Sayan Saha et al.	The Astrophysical Journal
2026-10-28	W4407785632	Supervising the search process produces reliable and generalizable information-seeking agents	Guangzhi Xiong et al.	Nature Communications
2026-10-27	2610.37381	PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations	Hanqing Wang et al.	arXiv	152
2026-10-27	2610.36729	Hy-Nomas: Towards Free-form Interactive World Generation	Qiaoling Chen et al.	arXiv	122
2026-10-27	2610.35845	Work Agents: Systems, Capabilities, and Optimization	Zishan Xu et al.	arXiv	115
2026-10-27	2610.36671	Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs	Donghyeon Cho et al.	arXiv	100
2026-10-27	2610.34662	StreamVibe: Proactive Video Agents for Evolving User Intent	Chengzhi Liu et al.	arXiv	95
2026-10-27	2610.37230	TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving	Shuhuai Li et al.	arXiv	77
2026-10-27	2610.32285	Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution	Zhiyong Cao et al.	arXiv	66
2026-10-27	2610.37666	ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning	Chaehyun Kim et al.	arXiv	64
2026-10-27	2610.33966	InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants	Qinsi Wang et al.	arXiv	56
2026-10-27	2610.33956	Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents	Haoyu Zhao et al.	arXiv	54
2026-10-27	2610.37341	CodeCap-Bench: Can Code Serve as a Good Video Caption?	Jiafu Tang et al.	arXiv	52
2026-10-27	2610.34415	Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion	Kam Man Wu et al.	arXiv	50
2026-10-27	2610.33135	WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control	Lei Cao et al.	arXiv	50
2026-10-27	2610.36456	LociArt: A Unified Paradigm for Free-Style Local Video Stylization	Yuxuan Chen et al.	arXiv	48
2026-10-27	2610.33512	Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL	Hyun Ryu et al.	arXiv	47
2026-10-27	2610.34467	DynaFlow: Learning Free-Form Multi-Agent Orchestration	Ruhao Liu et al.	arXiv	47
2026-10-27	2610.33568	Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents	Yihao Hu et al.	arXiv	44
2026-10-27	2610.33413	AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos	Yuesheng Huang et al.	arXiv	43
2026-10-27	2610.32195	Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery	Dongki Kim et al.	arXiv	40
2026-10-27	2610.37161	WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training	Ziyang Zeng et al.	arXiv	36
2026-10-27	2610.35518	S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning	Shuo Shen et al.	arXiv	33
2026-10-27	2610.31635	HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction	Zunnan Xu et al.	arXiv	33
2026-10-27	2610.33472	Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement	Zekai Zhang et al.	arXiv	33
2026-10-27	2610.33169	World-in-Context: Interactive Video World Modeling with In-Context Conditioning	Harold Haodong Chen et al.	arXiv	32
2026-10-27	2610.37037	Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception	Lai Wei et al.	arXiv	31
2026-10-27	2610.33845	Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players	Changlian Ma et al.	arXiv	30
2026-10-27	2610.37364	EmbeddingGemma 2: Unified and Efficient Multimodal Representations	Henrique Schechter Vera et al.	arXiv	30
2026-10-27	2610.36466	Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation	Shufan Li et al.	arXiv	30
2026-10-27	2610.19025	How Far Can Coding Agents Go in Visual Generation?	Hengguang Zhou et al.	arXiv	29
2026-10-27	2610.37662	Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?	Jialv Zou et al.	arXiv	29
2026-10-27	2610.33024	Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation	Zhihao Yang et al.	arXiv	27
2026-10-27	2610.34356	RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions	Haoyu Zhao et al.	arXiv	26
2026-10-27	2610.34238	Δτ-Bench: Pushing Agents Toward a Moving Capability	Shuofei Qiao et al.	arXiv	24
2026-10-27	2610.35193	Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges	Jiayue Pu et al.	arXiv	23
2026-10-27	2610.18683	ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning	Bowen Ding et al.	arXiv	22
2026-10-27	2610.33608	Mycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities	Julia Belikova et al.	arXiv	21
2026-10-27	2610.23928	miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning	Zhen Li et al.	arXiv	20
2026-10-27	2610.35001	More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation	Yuzhuo Chen et al.	arXiv	19
2026-10-27	2610.14018	RoboHarness: A Simple Harness Outperforms VLA and World Action Models	Bince Qu et al.	arXiv	19
2026-10-27	2610.35864	VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation	Muxi Diao et al.	arXiv	19
2026-10-27	2610.29915	CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion	Kai Zhu et al.	arXiv	17
2026-10-27	2610.31309	Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization	Jiacheng Liu et al.	arXiv	17
2026-10-27	2610.34735	iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents	Yuting Ning et al.	arXiv	16
2026-10-27	2610.33861	ReGE: Stronger Agents through Experience Synthesis	Jiarong Liang et al.	arXiv	14
2026-10-27	2610.34654	Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents	Nghi D. Q. Bui	arXiv	14
2026-10-27	2610.35385	EmbodiedLab: Benchmarking Embodied Agents That Act to Know	Hongcheng Gao et al.	arXiv	14
2026-10-27	2610.29139	Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model	Jiongxiao Wang et al.	arXiv	14
2026-10-27	2610.34386	ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?	Haojin Wang et al.	arXiv	12
2026-10-27	2610.33079	Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access	Zetian Song et al.	arXiv	12
2026-10-27	2610.34634	AgentProofBench: Benchmarking Reusable Verifiers for Web Agents	Jingjie Ning et al.	arXiv	12
2026-10-27	2610.33503	Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination	Qiyao Wang et al.	arXiv	12
2026-10-27	2610.31818	Nested Sparsity for Scalable Pretraining and Continual Learning	Tianzhe Chu et al.	arXiv	11
2026-10-27	2610.21240	Representation Redistribution in Sparse Autoencoders	Ziye Mei et al.	arXiv	9
2026-10-27	2610.34577	Rethinking Verification in Agent Harnesses	Zhengxin Zhang et al.	arXiv	9
2026-10-27	2610.21561	DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents	Sergio Burdisso et al.	arXiv	9
2026-10-27	2610.30970	Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters	Tardelli Ronan Coelho Stekel	arXiv	9
2026-10-27	2610.34241	Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?	Vaibhav Jain	arXiv	9
2026-10-27	2610.32004	CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments	Monojit Banerjee et al.	arXiv	8
2026-10-27	2610.35434	Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization	Wangcheng Tao et al.	arXiv	8
2026-10-27	2610.33718	RoboJev: An Open Vision-Language Judge for Robot Success Detection	Josef Liyanjun Chen	arXiv	7
2026-10-27	2610.35328	Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance	Ngoc Trinh Hung Nguyen et al.	arXiv	7
2026-10-27	2610.33005	OpenESM: Energy-Steered Models Are Scalable Foundation Learners	Yuan Pu et al.	arXiv	6
2026-10-27	2610.35450	OBB-PBD: Extending Parallel Box Decoding to Oriented Bounding Boxes for Referring Expression Grounding in Aerial Imagery	Chang Woo Song et al.	arXiv	5
2026-10-27	2610.34638	Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila	Declan Kutscher et al.	arXiv	4
2026-10-27	2610.33732	Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5	Georgios Feretzakis et al.	arXiv	4
2026-10-27	2610.24451	Assessing the CAD Capabilities of General-Purpose AI Models: A Case Study of GPT-6 Astra	Qiang Zou et al.	arXiv	4
2026-10-27	2610.35295	Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models	Zikai Zhou et al.	arXiv	3
2026-10-27	2610.17117	Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations	Bryce Grant et al.	arXiv	3
2026-10-27	2610.33877	Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning	Yehonatan Elisha et al.	arXiv	3
2026-10-27	2610.31566	CellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Models	Ilan Theodoro et al.	arXiv	2
2026-10-27	2610.32177	Ψ-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model	Khai Loong Aw et al.	arXiv	2
2026-10-27	2610.33817	EnvLunch: The Environment as a Free Lunch for Learning to Interact	Wei Liu et al.	arXiv	2
2026-10-27	2610.34886	ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning	Rhea Sanjay Sukthanker et al.	arXiv	2
2026-10-27	2610.34149	Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?	Tianchen Guo et al.	arXiv	2
2026-10-27	2610.28490	Learning from Automatic 3D Gaussian Splatting Edits for Online Bayesian Scene Change Detection	Changrui Zhu et al.	arXiv	1
2026-10-27	W4286750915	A model predictive control framework with robust stability guarantees under unbounded disturbances	Johannes Köhler et al.	Automatica
2026-10-27	W7154733918	Ultrafast Charge, Spin, and Lattice Coupling Facilitates Spin Transport as Magnon–Polarons in Yttrium Iron Garnet	Harshad Gajapathy et al.	Angewandte Chemie International Edition
2026-10-27	W7163903130	Unravelling the Role of Stacking Disorder on the Optoelectronic Properties of Zn3P2	Francesco Salutari et al.	Chemistry of Materials
2026-10-26	2610.35684	OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images	Junyeong Ahn et al.	arXiv	120
2026-10-26	2610.36068	Rollback: Experience Backtracking in World Models for Policy Improvement	Jiayi Luo et al.	arXiv	81
2026-10-26	2610.30932	UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents	Jujia Zhao et al.	arXiv	63
2026-10-26	2610.31162	HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games	Zecong Tang et al.	arXiv	58
2026-10-26	2610.32965	RynnUnify: Towards Unified Embodied Brain	Minghao Zhu et al.	arXiv	55
2026-10-26	2610.31668	Reading, Writing, Sharing, and Interacting with the World through Video	Shengqiong Wu et al.	arXiv	49
2026-10-26	2610.32253	RSIHub: A Composable Framework for Agent-Evolution Methods	Zimu Wang et al.	arXiv	49
2026-10-26	2610.32770	On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models	Leon Sick et al.	arXiv	45
2026-10-26	2610.36077	The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents	Weidong Tang et al.	arXiv	44
2026-10-26	2610.19687	Function-Space Temporal Self-Distillation for Policy Optimization	Aryan Das et al.	arXiv	38
2026-10-26	2610.31066	Dual Exam: Controlled Evaluation of Multimodal Agents and World Models	Zhefan Rao et al.	arXiv	34
2026-10-26	2610.22543	On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction	Eliezer Shlomi et al.	arXiv	34
2026-10-26	2610.27103	Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs	Zijian Liu et al.	arXiv	33
2026-10-26	2610.32093	DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning	Minho Park et al.	arXiv	31
2026-10-26	2610.31734	DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model	Zixian Gao et al.	arXiv	31
2026-10-26	2610.35013	Multiscale Policy Optimization for Long-Horizon LLM Agents	Tao Ren et al.	arXiv	30
2026-10-26	2610.31819	Speculative Diffusion is a Tale of Two Tradeoffs	Aaron Zorel et al.	arXiv	26
2026-10-26	2610.31931	Every Weight Is a Path of Shared Discrete Decisions	Ammar Ali et al.	arXiv	25
2026-10-26	2610.34724	Harness-Model Collaboration for Long-Horizon Continual Learning	Zhen Bi et al.	arXiv	21
2026-10-26	2610.29477	TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics	Yegor Anichkov et al.	arXiv	20
2026-10-26	2610.36269	Cross-modal Steering Vectors Exist Across Both Image and Text Generation	Donghao Zeng et al.	arXiv	20
2026-10-26	2610.35138	Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models	Xilin Wei et al.	arXiv	20
2026-10-26	2610.32002	DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation	Siyang He et al.	arXiv	19
2026-10-26	2610.01352	MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning	Juekai Lin et al.	arXiv	16
2026-10-26	2610.31423	FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models	Huixin Xu et al.	arXiv	15
2026-10-26	2610.14253	SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing	Arman Zarei et al.	arXiv	14
2026-10-26	2610.30006	Building Auditable AI Text Detectors with Sparse Autoencoders	Liam Dugan et al.	arXiv	14
2026-10-26	2610.29552	Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding	Xin Zhang et al.	arXiv	14
2026-10-26	2610.23234	MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation	Yuhan Sun et al.	arXiv	13
2026-10-26	2610.24481	DuoLM: Fast and Effective Personalized Recommendation with Language Models	Jiang Wu et al.	arXiv	12
2026-10-26	2610.17821	FLOMSS: Generative Music Source Separation by Flow Matching	Shuyang Cui et al.	arXiv	12
2026-10-26	2610.31569	Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models	Yufeng Liu et al.	arXiv	12
2026-10-26	2610.21109	Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows	Shirley Anugrah Hayati et al.	arXiv	11
2026-10-26	2610.30524	LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification	Zhipeng Cao et al.	arXiv	11
2026-10-26	2610.19589	JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making	Zhongwei Xie et al.	arXiv	11
2026-10-26	2610.32250	Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction	Ziang Zhang et al.	arXiv	11
2026-10-26	2610.31810	PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean	Jiyuan Tan et al.	arXiv	9
2026-10-26	2610.27782	RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation	Siyuan Ma et al.	arXiv	9
2026-10-26	2610.14465	Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval	Zhisheng Qi et al.	arXiv	9
2026-10-26	2610.31288	DISC: Domain-Integrated Similarity Cost for Time-Series Dataset	Yen-Ku Liu et al.	arXiv	8
2026-10-26	2609.16158	The fixed-point bundle method over product-of-simplex domains arising from game equilibria	Hongbo Sun	arXiv	8
2026-10-26	2610.20117	KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks	Lukas Niehaus et al.	arXiv	7
2026-10-26	2610.32909	HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training	Xihan Ma et al.	arXiv	7
2026-10-26	2610.25118	How Much Feedback Is Needed to Break Template Protection? The Geometric Vulnerability of Biometric Authentication	Eliron Rahimi et al.	arXiv	6
2026-10-26	2610.31716	Does LeWorldModel Preserve Local Action Geometry?	Vasil Vasilev et al.	arXiv	6
2026-10-26	2610.28655	What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories	Koutian Wu et al.	arXiv	5
2026-10-26	2606.00778	A path-following framework on fiber bundle for variational inequalities	Hongbo Sun	arXiv	5
2026-10-26	2610.32894	LoCA: Enabling Multi-Modality in Geospatial Location Encoders	Panagiotis Koromilas et al.	arXiv	5
2026-10-26	2610.27364	Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection	Mosh Levy et al.	arXiv	4
2026-10-26	2610.27528	Judging the Justification: Decision Certificate Supervision for Generative Reward Models	Guiquan Sun et al.	arXiv	4
2026-10-26	2610.31572	On the Token Collapse Phenomenon in Textual Graph Soft Prompting	Andrea Giuseppe Di Francesco et al.	arXiv	3
2026-10-26	2610.31779	FLORA: An Open Model Suite for Scaling Robotics Data Engines	Sicong Leng et al.	arXiv	3
2026-10-26	2610.27597	WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot	Bo Zou et al.	arXiv	2
2026-10-26	W4362707108	Inst-Inpaint: Instructing to Remove Objects with Diffusion Models	Ahmet Burak Yildirim et al.	International Journal of Computer Vision
2026-10-26	W4404451325	Noise-driven odd elastic waves in living chiral active matter	Sang Hyun Choi et al.	Physical Review Letters
2026-10-26	W4323542464	One-shot learning of paired association navigation with biologically plausible schemas	Moorthy Ganeshkumar et al.	Journal of Neuroscience
2026-10-26	W4385460888	Loss of PAX6 alters the excitatory/inhibitory neuronal ratio in human cerebral organoids	Wai Kit Chan et al.	Development
2026-10-25	2610.34283	ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence	Yihao Hu et al.	arXiv	74
2026-10-25	2610.34491	What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents	Kaiser Sun et al.	arXiv	32
2026-10-25	2610.34073	Memory Tax: Dissecting the Net Value of Agent Memory	Xuan He et al.	arXiv	29
2026-10-25	2610.34186	HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience	Yang Liu et al.	arXiv	29
2026-10-24	2610.33624	RSI Arena: Towards Recursive Self-Improvement with Human Feedback	Yue Huang et al.	arXiv	37
2026-10-24	W7223290560	How the Porous Transport Layer Dictates Membrane Electrode Assembly Performance of IrO 2 Catalysts	Hyeseong Jeon et al.	Advanced Functional Materials
2026-10-23	2610.30181	Deep Search in Real-World Web Environments	Xiaomin Yu et al.	arXiv	130
2026-10-23	2610.32749	Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes	Wendi Sang et al.	arXiv	123
2026-10-23	2610.30949	IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems	A. Jian Yang et al.	arXiv	99
2026-10-23	2610.25100	Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models	Rubin Wei et al.	arXiv	54
2026-10-23	2610.27851	LaLa-World: Scaling Latent World Models with Natural Language Actions	Junha Song et al.	arXiv	50
2026-10-23	2610.30926	Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation	Songlin Yang et al.	arXiv	50
2026-10-23	2610.31329	WeVisOne-VL: Unified Visual Perception from Objects to Pixels	Tianming Liang et al.	arXiv	48
2026-10-23	2610.30320	Self-Distilling Future Video Representations for World Action Models	Huiwon Jang et al.	arXiv	47
2026-10-23	2610.23987	What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models	Tengju Ru et al.	arXiv	40
2026-10-23	2610.27598	Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE	Ermo Hua et al.	arXiv	40
2026-10-23	2610.31670	Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success	Yunfei Xie et al.	arXiv	38
2026-10-23	2610.24738	Editing Images into Reusable Layers via Compositional Edit-Prior Distillation	Wen Xue et al.	arXiv	35
2026-10-23	2601.15351	OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning	Md Khairul Islam et al.	arXiv	35
2026-10-23	2610.28416	Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V	Zhenghan Chen et al.	arXiv	34
2026-10-23	2610.29677	Toward Recursive Self-Improvement in Physical AI	Meng Luo et al.	arXiv	32
2026-10-23	2610.30755	Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought	Zhengye Bao et al.	arXiv	31
2026-10-23	2610.28889	Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks	Ivan Listopadov et al.	arXiv	30
2026-10-23	2610.30753	FilmFlow: Agentic System for 3D Virtual Film Cinematography	Yiming Zhang et al.	arXiv	29
2026-10-23	2610.27712	RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting	Injae Kim et al.	arXiv	28
2026-10-23	2610.32411	A Broader Look into MLLM's Retrieval Heads	Jia Wang et al.	arXiv	28
2026-10-23	2610.26233	Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents	Zhenyu Zhang et al.	arXiv	27
2026-10-23	2610.31158	Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports	Jiahao Meng et al.	arXiv	26
2026-10-23	2610.19705	RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing	Xiaohan Wang et al.	arXiv	25
2026-10-23	2610.31062	SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs	Arnon Mazza et al.	arXiv	25
2026-10-23	2610.30418	Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems	Daniel Ruiz et al.	arXiv	24
2026-10-23	2610.25835	Diffusion Language Models Change Speed Across Tasks and Languages	Mohsen Fayyaz et al.	arXiv	21
2026-10-23	2610.31305	Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation	Hongcan Guo et al.	arXiv	21
2026-10-23	2610.31574	Rethinking Sequence Compression with Test-time Regression	Sihan Yang et al.	arXiv	21
2026-10-23	2610.32046	Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?	Yepeng Liu et al.	arXiv	21
2026-10-23	2610.04184	EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?	Yaolun Zhang et al.	arXiv	19
2026-10-23	2610.31198	Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models	Ofek Avivi et al.	arXiv	19
2026-10-23	2610.31494	AgentVQA: A Unified Benchmark for Agentic Visual Understanding	Advait Gupta et al.	arXiv	18
2026-10-23	2610.31466	AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark	Ruicong Liu et al.	arXiv	17
2026-10-23	2610.30866	Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos	Zhuoran Zhang et al.	arXiv	17
2026-10-23	2610.26252	SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS	Walaa Othman et al.	arXiv	16
2026-10-23	2610.30882	Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models	Zhizhuo Kou et al.	arXiv	16
2026-10-23	2610.20091	RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation	Jaeyeon Heo et al.	arXiv	15
2026-10-23	2610.31623	F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation	Jinyu Zhang et al.	arXiv	15
2026-10-23	2610.22951	MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models	Khuyen Pham et al.	arXiv	14
2026-10-23	2610.30340	Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles	NVIDIA et al.	arXiv	14
2026-10-23	2610.20459	MolLean: A Process-Verifiable Language for Chemical Reasoning	Jiatong Li et al.	arXiv	13
2026-10-23	2610.31372	RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention	Jiening Siow et al.	arXiv	12
2026-10-23	2610.30468	SplatLab: Autonomous Scientific Discovery for 3DGS Research	Seemandhar Jain et al.	arXiv	11
2026-10-23	2610.24383	IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems	Jie Mao et al.	arXiv	9
2026-10-23	2610.31651	BrickWright: Agentic Creation of Physically Feasible Brick Builds	Ava Pun et al.	arXiv	9
2026-10-23	2610.25376	TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models	Yuxiang Lu et al.	arXiv	8
2026-10-23	2610.31474	Skeleton-Grounded Latent Action Model for Robot World Models	Qi Lv et al.	arXiv	8
2026-10-23	2610.22722	The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems	Georgios Politis et al.	arXiv	7
2026-10-23	2610.24385	Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization	Jie Mao et al.	arXiv	6
2026-10-23	2610.27148	Who Takes the Lead? Model Ability and Task-Conditioned Collaboration with Humans	Weien Li et al.	arXiv	6
2026-10-23	2610.31576	What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models	Jinya Sakurai et al.	arXiv	6
2026-10-23	2610.28950	HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second	Jonas Eschmann et al.	arXiv	5
2026-10-23	2610.12586	Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective	Dmitry Osin et al.	arXiv	3
2026-10-23	2610.30043	TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments	Yicheng Xu et al.	arXiv	2
2026-10-22	2610.28577	Cache Engineering for Agents	Tianyu Fu et al.	arXiv	132
2026-10-22	2610.26659	SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?	Zhaoxi Zhang et al.	arXiv	120
2026-10-22	2610.26828	Agent World Model in the Wild: Computer-Use Agent Environment Synthesis	Zhaoyang Wang et al.	arXiv	99
2026-10-22	2610.29989	Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation	Ruopeng Gao et al.	arXiv	92
2026-10-22	2610.28698	Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds	Kuan Zhang et al.	arXiv	85
2026-10-22	2610.20538	PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis	Qiushi Sun et al.	arXiv	69
2026-10-22	2610.21114	Spectral-Spatial Interpretation	Haotian Ma et al.	arXiv	63
2026-10-22	2610.29997	DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations	Mingze Sun et al.	arXiv	57
2026-10-22	2610.28402	StreamEval: Evaluating Interactive Streaming Video Generation Models	StreamEval Team	arXiv	55
2026-10-22	2610.29722	Retrieval Augmented Generation Compositionality	Ido Levy et al.	arXiv	48
2026-10-22	2610.29680	TraceForge: Distilling with Your Own Thinking	Yan Wang	arXiv	47
2026-10-22	2610.17860	Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills	Letian Zhu et al.	arXiv	45
2026-10-22	2610.28589	AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics	Xinxin Liu et al.	arXiv	44
2026-10-22	2610.28887	Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures	Yujian Liu et al.	arXiv	40
2026-10-22	2610.29968	CulturalRiddles: A Multicultural Benchmark of Riddles	My Chiffon Nguyen et al.	arXiv	40
2026-10-22	2610.29357	Memory-Centric Continual Learning for AI Agents	Dongfang Li et al.	arXiv	40
2026-10-22	2610.11942	Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents	Jiaming Zhang et al.	arXiv	36
2026-10-22	2610.30128	Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation	Zhanshuo Cao et al.	arXiv	30
2026-10-22	2610.30120	ALPS: Visual State Encoders for World Models	Yanqing Liu et al.	arXiv	30
2026-10-22	2610.28711	Qwen-Audio-3.1-ASR Technical Report	Chuanmeng Bian et al.	arXiv	28
2026-10-22	2610.28679	VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents	Jianing Yin et al.	arXiv	27
2026-10-22	2610.28763	Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?	Ming Zhong et al.	arXiv	27
2026-10-22	2610.29458	Harness Scaling for Generalizable Agentic Reinforcement Learning	Fei Bai et al.	arXiv	23
2026-10-22	2610.29560	From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation	Tingwen Du et al.	arXiv	22
2026-10-22	2610.30108	Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use	Yanzhe Chen et al.	arXiv	22
2026-10-22	2610.33106	VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team	Wenbo Hu et al.	arXiv	22
2026-10-22	2610.19376	DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents	Tianle Chen et al.	arXiv	21
2026-10-22	2610.29441	Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers	Tianze Xia et al.	arXiv	21
2026-10-22	2610.23344	Language Models Learn to Improve Language Models	Minhua Lin et al.	arXiv	20
2026-10-22	2610.13177	CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction	Bing He et al.	arXiv	20
2026-10-22	2610.30023	RealMe: Immersive Volumetric Video from Minimal Captures	Chenxu Zhou et al.	arXiv	20
2026-10-22	2610.27592	Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?	Xingsong Ye et al.	arXiv	20
2026-10-22	2610.29545	PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States	Patrick Haller et al.	arXiv	19
2026-10-22	2610.30136	Agentic World Action Models	Zhuoyang Liu et al.	arXiv	18
2026-10-22	2610.28940	StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion	Yisi Liu et al.	arXiv	16
2026-10-22	2610.27227	Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams	Yanan Ma et al.	arXiv	15
2026-10-22	2610.28905	Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication	Alan-Barsag Gazzaev et al.	arXiv	14
2026-10-22	2610.21204	Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally	Zhizhuo Kou et al.	arXiv	14
2026-10-22	2610.29317	SpatialBrain: Spatial Intelligence Growing from Experience	Yifan Zhou et al.	arXiv	13
2026-10-22	2610.28827	WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State	Xiaoxiao Ma et al.	arXiv	11
2026-10-22	2610.29784	Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting	Zhipeng Chen et al.	arXiv	11
2026-10-22	2610.27040	ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models	Yinhe Wang et al.	arXiv	11
2026-10-22	2610.09861	Toward Part-Aware Choral Transcription with singing voice assignment	Hanyu Meng et al.	arXiv	11
2026-10-22	2610.29934	ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination	Nithin Sivakumaran et al.	arXiv	10
2026-10-22	2610.30066	Looped Uniform Diffusion Language Models	Saiteja Utpala et al.	arXiv	9
2026-10-22	2610.29434	RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding	Chihiro Arata et al.	arXiv	9
2026-10-22	2610.28909	DiffResearch: Accelerating Deep Research with Diffusion Language Models	Alan-Barsag Gazzaev et al.	arXiv	8
2026-10-22	2610.30113	Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research	Houde Qian et al.	arXiv	8
2026-10-22	2610.28474	Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training	Zhizhuo Kou et al.	arXiv	8
2026-10-22	2610.28441	Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity	Sahil Joshi et al.	arXiv	7
2026-10-22	2610.28027	From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks	Taiheng Pan	arXiv	6
2026-10-22	2610.30090	VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift	Juan S. Santillana	arXiv	5
2026-10-22	2610.27233	MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows	Ruoxin Wang et al.	arXiv	4
2026-10-22	2610.26397	Bridged Self-Distillation for On-Policy Learning	Runsheng Chen et al.	arXiv	4
2026-10-22	2610.29932	FrontierCS 2: A Benchmark for Computer Science R&D	Qiuyang Mang et al.	arXiv	4
2026-10-22	2610.24771	Design Anything, Design at Scale	Xuchao Ren et al.	arXiv	4
2026-10-22	2610.26836	Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy	Ke Zhang et al.	arXiv	3
2026-10-22	2610.22659	Exploring The Empirical Privacy Landscape of Synthetic Data	Zihao Zhao et al.	arXiv	3
2026-10-22	2610.27861	RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation	Haocheng Wang et al.	arXiv	1
2026-10-22	W7223226610	Wireless electrocatalytic closed-loop system for drug-free management of diabesity	Debasis Maity et al.	Science
2026-10-22	W7223221580	Antidopaminergic Medications and Clinical Outcomes in Huntington Disease	Karen Elta Anderson et al.	Neurology
2026-10-22	W7223179007	High false sign rates in transcriptome-wide association studies	P. Gerlach et al.	Nature Genetics
2026-10-22	W7155554427	DeepDive: Simultaneous Formation of Massive Quiescent Galaxies in High-redshift Galaxy Overdensities	Takumi Kakimoto et al.	The Astrophysical Journal
2026-10-22	W4417175683	Sequential diagnosis with language models	Harsha Nori et al.	Science
2026-10-22	W4404313154	Electronic bound states in the continuum in a two-dimensional metal	Morgan Thinel et al.	Science
2026-10-21	2610.27999	Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds	Jihai Zhang et al.	arXiv	101
2026-10-21	2610.28578	Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition	Wenjie Lou et al.	arXiv	72
2026-10-21	2610.26855	Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience	Tianqi Liu et al.	arXiv	62
2026-10-21	2610.28594	Learning the 4D World through Point Trajectory Forecasting	Byungwoo Jeon et al.	arXiv	53
2026-10-21	2610.28630	SolarRenderer: Few-Step Generative Reference Rendering	Guian Fang et al.	arXiv	51
2026-10-21	2610.25078	CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?	Jiaqi Su et al.	arXiv	49
2026-10-21	2610.14136	Correction Training for Diffusion Models	Donghoon Ahn et al.	arXiv	47
2026-10-21	2610.27628	PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking	Pan Wang et al.	arXiv	42
2026-10-21	2610.28354	S-Agent 2.0: Spatial Reasoning with a General Coding Agent	Rui Gong et al.	arXiv	39
2026-10-21	2610.26203	Focused Omni-Modal GUI Agents	Fuyao Zhang et al.	arXiv	39
2026-10-21	2610.25844	SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation	Yanjin He et al.	arXiv	34
2026-10-21	2610.27911	MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records	Seohyun Lee et al.	arXiv	32
2026-10-21	2610.28632	Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs	Noam Rotstein et al.	arXiv	27
2026-10-21	2610.28444	EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning	Xiaoxing Hu et al.	arXiv	27
2026-10-21	2511.14102	Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading	Wenfeng Wang et al.	arXiv	26
2026-10-21	2610.16523	EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents	Min Cai et al.	arXiv	25
2026-10-21	2610.18604	LLM2R: From Large Language Models to 3D Reassemblers	Zhouhan Zhong et al.	arXiv	25
2026-10-21	2610.26837	SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration	Javad Rajabi et al.	arXiv	25
2026-10-21	2610.28522	DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems	Xialie Zhuang et al.	arXiv	25
2026-10-21	2610.26067	PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning	Yuanhang Lei et al.	arXiv	24
2026-10-21	2610.24944	Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research	Yue Huang et al.	arXiv	23
2026-10-21	2610.27450	Ask to Distill: Learning to Synthesize Data for On-Policy Distillation	Jiashuo Sun et al.	arXiv	22
2026-10-21	2610.28601	Evolving Agent Interfaces	Saaket Agashe et al.	arXiv	22
2026-10-21	2610.26542	Breaking Diffusion: Parallel Reasoning with Draft Refinement	Jaesang Yu et al.	arXiv	22
2026-10-21	2610.28069	Training the Whole Agent, Not Just the Model	Lingxiao Tang et al.	arXiv	19
2026-10-21	2610.28559	Large Flow Language Models	Arnav Chavan et al.	arXiv	19
2026-10-21	2609.34565	FlowState: Execution State as Memory for Long-Horizon LLM Agents	Minghao Li et al.	arXiv	18
2026-10-21	2610.24628	Muse Glimmer 30B: An On-Device Agentic Model	Arash Ebrahim Abtahizadeh et al.	arXiv	18
2026-10-21	2610.22444	Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning	Yizhe Zhang et al.	arXiv	17
2026-10-21	2610.25369	Painting Change Map as guidance for generating painting processes	Markus Pobitzer et al.	arXiv	17
2026-10-21	2610.26681	From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping	Zekai Luo et al.	arXiv	17
2026-10-21	2610.24648	EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends	Yuhua Zheng et al.	arXiv	15
2026-10-21	2610.26426	HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL	Xiaoqiang Wang et al.	arXiv	14
2026-10-21	2610.28388	Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling	Fangcong Yin et al.	arXiv	13
2026-10-21	2610.27406	More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents	Ruhan Wang et al.	arXiv	13
2026-10-21	2610.27435	Harness Self-Evolution for Long-Horizon Terminal Agents	Ruhan Wang et al.	arXiv	13
2026-10-21	2610.25043	VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse	Sicheng He et al.	arXiv	13
2026-10-21	2610.27360	On the Limits of Scale: Inverse Scaling in Vision-Language Models	Rohit Saxena et al.	arXiv	12
2026-10-21	2610.27190	On the Fragility of Tasks under Composition: Implicit Budgeting in Language Models	Chenpan Li et al.	arXiv	11
2026-10-21	2610.19425	Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach	Jiarui Qin et al.	arXiv	10
2026-10-21	2610.27327	Unsupervised Tool Evolution for Coding Agents in Data-Lake Analytics	Yuqing Yang et al.	arXiv	10
2026-10-21	2610.24899	HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents	Soyoung Yoon et al.	arXiv	10
2026-10-21	2610.24649	Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success	Naman Vats	arXiv	9
2026-10-21	2610.23400	On the Tip of the Tongue: First-Token Cueing as a Behavioral Probe of Recall Failures in LLMs	Jaewon Sok et al.	arXiv	7
2026-10-21	2610.26711	PVBench: Quantifying Physical Plausibility in Video Generation with Object-Level Physical Measurements	Kaiwei Chen et al.	arXiv	7
2026-10-21	2610.07609	PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation	Yu Zhang et al.	arXiv	6
2026-10-21	2606.31002	Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization	Ke Zhang et al.	arXiv	6
2026-10-21	2610.25519	ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference	Mobina Kashaniyan et al.	arXiv	5
2026-10-21	2610.28554	OverSeer: Multi-Agent World Models Beyond What Agents See	Runjia Li et al.	arXiv	5
2026-10-21	2610.18950	λ_0: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation	humanoid Team	arXiv	5
2026-10-21	2610.28435	Multimodal Reranking Is a System One Decision	Zhuchenyang Liu et al.	arXiv	5
2026-10-21	2610.27334	EMBER: Predicting TCR--pMHC Binding Without a Docked Complex	Lin Ha et al.	arXiv	5
2026-10-21	2610.28074	Slot-JEPA: Object-Structured Prediction Interfaces for Latent World Models	Peisong Wen et al.	arXiv	4
2026-10-21	2610.24519	Axiomatic World Modeling for Physics Reasoning	Xinye Yang et al.	arXiv	3
2026-10-21	2610.27914	World Models with Configurable Perception	Yijun Shen et al.	arXiv	3
2026-10-21	2610.26857	VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token	Sangbeom Lim et al.	arXiv	3
2026-10-21	2610.28284	HRoPE: Homography Relative Positional Encoding	Huachen Gao et al.	arXiv	3
2026-10-21	2610.19419	WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding	Chenxu Wang et al.	arXiv	3
2026-10-21	2610.23010	What Makes a Good Symbol for Hybrid Discrete-Continuous Planning?	Yiyuan Pan et al.	arXiv	2
2026-10-21	2610.24452	HumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time	unsu Kim et al.	arXiv	2
2026-10-21	2610.25765	TRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Prediction	Minjun Kim et al.	arXiv	2
2026-10-21	2603.19233	Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models	Bryce Grant et al.	arXiv	1
2026-10-21	2610.25459	BiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks	Yong Wang et al.	arXiv	1
2026-10-21	2610.09513	OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning	Zhenyang Liu et al.	arXiv	1
2026-10-21	W7155217162	Intra- and Interlayer Excitonic Fine Structure of the Two-Dimensional Perovskite (PEA)2PbI4	Patrick Grenzer et al.	Nano Letters
2026-10-21	W7154962243	Functional architecture of the human insula	Julian Quabs et al.	Nature
2026-10-21	W7223132653	Persistent neuronal stress signalling underlies Angelman syndrome phenotypes	Kwang‐Soo Kim et al.	Nature
2026-10-20	2610.26825	MemT-1.0: Towards Memory-Native Evolution	Zhiyu Li et al.	arXiv	142
2026-10-20	2610.25736	Learning from Fleet Experience: A Collective Learning Paradigm for Robots	Chao Yu et al.	arXiv	127
2026-10-20	2610.26860	OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory	Yu Zhou et al.	arXiv	115
2026-10-20	2610.26625	EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience	Xinhao Ji et al.	arXiv	55
2026-10-20	2610.22791	Self-Evolving Coding Agents via Harness-Policy Optimization	Zhepei Wei et al.	arXiv	54
2026-10-20	2610.24960	CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents	Zhongwei Xie et al.	arXiv	52
2026-10-20	2610.25690	ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation	Yihui Yang et al.	arXiv	50
2026-10-20	2610.26549	Holi-World: Building Holistic World Intelligence from Human-Ego Experience	Hao Li et al.	arXiv	49
2026-10-20	2610.24087	OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners	Peisong Wang et al.	arXiv	48
2026-10-20	2610.26844	AnyGoal: On World Model Generalization Beyond Expert Rollouts	Heejeong Nam et al.	arXiv	44
2026-10-20	2610.25404	MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion	Houyuan Chen et al.	arXiv	44
2026-10-20	2610.26802	Scaling Parameter-Efficient Fine-Tuning for Brain Encoding	Zhuofan Josh Ying et al.	arXiv	41
2026-10-20	2610.24520	HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory	Junming Zhang et al.	arXiv	41
2026-10-20	2610.06830	MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents	Haozhen Zhang et al.	arXiv	40
2026-10-20	2610.26216	RoAR-VAE: Improving Latent Diffusability through Robust Prediction	Yang Yue et al.	arXiv	40
2026-10-20	2610.26834	Kronecker Delta Rule for Long Context Linear Attention	Anamaria-Roberta Hartl et al.	arXiv	37
2026-10-20	2610.26824	SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum	Zhongxin Chen et al.	arXiv	35
2026-10-20	2610.23986	BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References	Xinyu Fang et al.	arXiv	34
2026-10-20	2610.25950	AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments	Rui Wang et al.	arXiv	33
2026-10-20	2610.26770	HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs	Zhuoshi Pan et al.	arXiv	31
2026-10-20	2610.26853	InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation	Yi-Chuan Huang et al.	arXiv	30
2026-10-20	2610.26851	Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning	Sheng-Wei Zhang et al.	arXiv	30
2026-10-20	2610.25011	FineSplat: Fine Patches, Local Groups, Detailed Splats	Hyebin Kim et al.	arXiv	29
2026-10-20	2606.31876	Harnessing Textual Refusal Directions for Multimodal Safety	Moreno D'Incà et al.	arXiv	25
2026-10-20	2610.26848	Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy	Zekai Li et al.	arXiv	24
2026-10-20	2610.16782	LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints	Ming Shin Cindy Sung et al.	arXiv	24
2026-10-20	2610.19686	Interlock: From Local Correctness to Task Completion in Long-Horizon Agents	Linji Hao et al.	arXiv	24
2026-10-20	2610.26663	RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models	Shengbang Liu et al.	arXiv	21
2026-10-20	2610.17724	Evidence-First Agentic Verification	Reza Sanayei et al.	arXiv	21
2026-10-20	2609.22332	AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation	Jiadi You et al.	arXiv	20
2026-10-20	2610.25090	Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation	Junwei Wen et al.	arXiv	19
2026-10-20	2610.26081	DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal	Deshui Miao et al.	arXiv	18
2026-10-20	2610.25525	StopLoss: Teaching Agents to Predict Failure and Stop Early	Jiarong Liang et al.	arXiv	16
2026-10-20	2610.26811	State World Models: Execute the Rules, Generate the Pixels	Chan Yan Ki et al.	arXiv	15
2026-10-20	2610.17816	Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution	Pengcheng Huang et al.	arXiv	15
2026-10-20	2610.25666	Frechet Forcing: Training Long-Horizon Streaming World Models from Short Clips	Yian Zhao et al.	arXiv	15
2026-10-20	2610.25060	Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On	Vahid Jebraeeli et al.	arXiv	14
2026-10-20	2610.24766	ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction	Yuxuan Zhou et al.	arXiv	14
2026-10-20	2610.04902	Self-Evaluating Recursive Agents	TianYi Lyu et al.	arXiv	14
2026-10-20	2610.22328	ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning	Sara Dorfman et al.	arXiv	13
2026-10-20	2610.26754	TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning	Liana Patel et al.	arXiv	11
2026-10-20	2610.23935	Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding	Jiakun Fan et al.	arXiv	11
2026-10-20	2610.20597	Co-Evolving Acting and Forecasting for Language Agents	Haofei Yu et al.	arXiv	11
2026-10-20	2610.22512	Predicting Privileged Information Effectiveness for On-Policy Self-Distillation	Kaijian Zou et al.	arXiv	10
2026-10-20	2610.19439	Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents	Yuanpu Cao et al.	arXiv	10
2026-10-20	2610.26830	Competing Learning in Hybrid Architectures	Xingyu Shen et al.	arXiv	9
2026-10-20	2610.24791	UniAVC: Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling	Kien T. Pham et al.	arXiv	8
2026-10-20	2610.26765	HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation	Tianwei Luo et al.	arXiv	8
2026-10-20	2610.16078	Heterogeneous Agentic Coevolution	Wenqian Ye et al.	arXiv	7
2026-10-20	2610.21810	N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models	Donghoon Han et al.	arXiv	7
2026-10-20	2610.21791	RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent	Huan Zhang et al.	arXiv	7
2026-10-20	2610.23600	Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable	Mengtan Zhang et al.	arXiv	7
2026-10-20	2610.25296	World Model Interpretability: From Decoding Representations to Understanding Latent Worlds	Jize Wang et al.	arXiv	7
2026-10-20	2610.06563	HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention	Han Luo et al.	arXiv	6
2026-10-20	2610.22324	Training Reasoning Models to Generate Diverse Scientific Ideas	Manya Wadhwa et al.	arXiv	6
2026-10-20	2610.25861	ActionRoPE: action as coordinates for spatially consistent control in planar-camera game world models	Zhiyang Deng et al.	arXiv	6
2026-10-20	2610.24611	HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference	Wanyi Chen et al.	arXiv	6
2026-10-20	2610.26453	Remembering Has a Price: Learning Memory Worth under Resource Constraints	Guannan Lai et al.	arXiv	6
2026-10-20	2610.22466	Harness-Delta Attribution: Dissecting Gains From Harness Evolution	Wenxuan Ding et al.	arXiv	5
2026-10-20	2610.19005	CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat	Bangya Liu et al.	arXiv	5
2026-10-20	2610.24133	A Conditional No-Hair Theorem for Transformers: How Language Models Forget Their Prompt	Shuyang Xiang	arXiv	5
2026-10-20	2610.26863	Text-to-Image Generative Modeling Without Language Pretraining	Keshigeyan Chandrasegaran et al.	arXiv	5
2026-10-20	2610.22894	Competence-Based Evaluation of Logical Reasoning in Large Language Models	Jize Jiang et al.	arXiv	4
2026-10-20	2610.09496	Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models	Jiho Lee et al.	arXiv	4
2026-10-20	2610.25874	Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation	Lingsen Zhang et al.	arXiv	4
2026-10-20	2610.23470	QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity	Takashi Ishida et al.	arXiv	4
2026-10-20	2610.25265	SPARC: Spoken Profile Authorship Recognition Corpus	Efthymios Tsaprazlis et al.	arXiv	4
2026-10-20	2610.23653	A Language-Informed Loss for Visual Generation	Suchir Agarwal et al.	arXiv	3
2026-10-20	2610.25159	Legal Guidance in the Wild: How Users Seek Legal Help in Real-World LLM Conversations	Amirreza Mohseni et al.	arXiv	3
2026-10-20	2610.22636	Measuring Mechanistic Uncertainty in Large Language Models via Causal Robustness	Aneesh Komanduri et al.	arXiv	3
2026-10-20	2604.11331	Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale	Dongxu Wei et al.	arXiv	3
2026-10-20	2610.19264	Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills	Ratnesh Pandey et al.	arXiv	3
2026-10-20	2610.25964	Token-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination Evaluation	Kesav Kumar Jayakumar et al.	arXiv	3
2026-10-20	2610.25288	Vision as Proprioception: Estimating Humanoid Robot Pose from Video	Jiaxi Jiang et al.	arXiv	2
2026-10-20	2610.22714	First Passage Attention	Yuxuan Liu	arXiv	1
2026-10-20	2610.14397	RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work	Andrew Perrault et al.	arXiv	1
2026-10-20	W7127923223	Simulation of boson sampling with optical feedback	Yu. A. Biriukov et al.	Physical Review A
2026-10-20	W7172541009	Multiancestry conditional and joint analysis applied to GWAS summary statistics	Xiaotong Wang et al.	Nature Genetics
2026-10-19	2610.22471	Has GPT-6-Astra Achieved Embodied Intelligence?	SenseNova et al.	arXiv	165
2026-10-19	2610.18784	Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents	Yuchen Lu et al.	arXiv	121
2026-10-19	2610.23374	MOSS-Image Technical Report	MOSI. AI	arXiv	101
2026-10-19	2610.23479	HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents	Hongcheng Gao et al.	arXiv	97
2026-10-19	2610.20951	LEV: Thinking Fast and Deep with Looped Decision Models	Dingjie Song et al.	arXiv	80
2026-10-19	2610.20424	BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business	Enhan Zhao et al.	arXiv	77
2026-10-19	2610.21783	Learning to Think and Explore in 3D World	Yijiang Li et al.	arXiv	71
2026-10-19	2610.19159	Into the Unknown: Benchmarking AI agents on open scientific research problems	Seungone Kim et al.	arXiv	62
2026-10-19	2610.23279	Xiaomi-Lens-0 Technical Report	Pei Fu et al.	arXiv	60
2026-10-19	2610.20556	Speculative Sampling in Interactive Video Generation	Yubo Huang et al.	arXiv	55
2026-10-19	2610.14157	OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools	Chenyang Yan et al.	arXiv	54
2026-10-19	2610.23181	Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning	Heming Zou et al.	arXiv	53
2026-10-19	2610.09872	LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets	Jun Zhao et al.	arXiv	52
2026-10-19	2610.21767	From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research	Yijia Mao et al.	arXiv	47
2026-10-19	2610.14746	BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries	Jiaxin Fang et al.	arXiv	44
2026-10-19	2610.21459	Can Visual Generation Expand What Unified Multimodal Models Know?	Wenkai Li et al.	arXiv	36
2026-10-19	2610.23230	RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars	Haonan Han et al.	arXiv	35
2026-10-19	2610.21046	PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews	Dingjie Song et al.	arXiv	34
2026-10-19	2610.23542	Execution Before Memory: Diagnosing Memory Failures in Video World Models	Weiyang Jin et al.	arXiv	32
2026-10-19	2610.22169	Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics	Jian Gu et al.	arXiv	30
2026-10-19	2610.23787	DLite: History-free Speculative Decoding for Agentic AI	Jiaming Xu et al.	arXiv	30
2026-10-19	2610.23751	MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing	Houyuan Chen et al.	arXiv	29
2026-10-19	2610.22448	Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards	Ruida Wang et al.	arXiv	24
2026-10-19	2610.09221	Consistent Distribution Matching for Data-Free Diffusion Distillation	Yuxiang Fu et al.	arXiv	23
2026-10-19	2610.23194	OfficeTown: Generative Organizations for Evolving Agent Intelligence	Hongchen Wei et al.	arXiv	23
2026-10-19	2610.22744	OmniXRef: A Unified Framework for Multimodal Multi-Reference Video Editing	Xiaoyan Cong et al.	arXiv	21
2026-10-19	2610.23036	Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design	Benhao Huang et al.	arXiv	19
2026-10-19	2610.23839	DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses	Jianyuan Zhong et al.	arXiv	19
2026-10-19	2610.23121	Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation	Xuanyu Liu et al.	arXiv	18
2026-10-19	2610.14022	OPMD: On-Policy Mechanism Distillation Beyond Output Supervision	Yingdong Shi et al.	arXiv	18
2026-10-19	2610.22602	Stuck on Shuffle: On Attribute-Object Binding in Vision-Language Models	Netanel Y. Tamir et al.	arXiv	18
2026-10-19	2610.21302	Dusting the Phantom: Gaussian Allocation for Fading Dynamic Content	Minhyeok Roh et al.	arXiv	18
2026-10-19	2610.05114	Belief-Trajectory Energy: Measuring the Path to a Prediction	Jiahao Ying et al.	arXiv	17
2026-10-19	2610.22428	Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models	Sai Kiran Bathula	arXiv	16
2026-10-19	2610.17184	DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck	Shubham Agarwal et al.	arXiv	16
2026-10-19	2610.21082	SciΠvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents	Youran Sun et al.	arXiv	15
2026-10-19	2610.20019	MorphAct: Robot Policies Morphing with the Worlds They Act In	Ziyan Liu et al.	arXiv	14
2026-10-19	2610.22321	AVC-Reward: Event-Centric Audio-Video Consistency Evaluation	Yuruo Wu et al.	arXiv	14
2026-10-19	2610.16071	Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems	Boxuan Zhang et al.	arXiv	13
2026-10-19	2610.22273	Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries	Anikait Singh et al.	arXiv	12
2026-10-19	2610.22234	OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents	Bowen Yang et al.	arXiv	12
2026-10-19	2610.20628	PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design	Phuong Tuan Dat et al.	arXiv	10
2026-10-19	2610.07052	BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking	Sudarshan Harithas et al.	arXiv	9
2026-10-19	2610.22708	GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations	Nicholas Saban et al.	arXiv	8
2026-10-19	2610.07898	FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents	Jia Liufu et al.	arXiv	8
2026-10-19	2610.19625	DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections	Xiaocong Yang et al.	arXiv	8
2026-10-19	2610.19636	Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching	Xiaocong Yang et al.	arXiv	8
2026-10-19	2610.22732	TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents	Aaron J. Li et al.	arXiv	7
2026-10-19	2610.16402	EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications	David Nukrai et al.	arXiv	7
2026-10-19	2610.18082	Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents	Xiyang Wu et al.	arXiv	7
2026-10-19	2610.19432	Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction	Lingfei Qian et al.	arXiv	6
2026-10-19	2610.20503	ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models	Bohan Sun et al.	arXiv	5
2026-10-19	2610.23795	Persistent Planar Memory for Video World Models	Yuze He et al.	arXiv	5
2026-10-19	2610.18834	Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?	Qingan Liu et al.	arXiv	5
2026-10-19	2610.19378	Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning	Vahid Jebraeeli et al.	arXiv	4
2026-10-19	2610.22697	What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics	Umar Iqbal	arXiv	4
2026-10-19	2610.21073	Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files	Xiaocong Yang et al.	arXiv	4
2026-10-19	2610.21189	Resisting Harmful Instructions through Training-Free Weight Editing	Ali Ebrahimpour-Boroojeny et al.	arXiv	4
2026-10-19	2610.22029	Selection Is Not Learning: Choosing Model Futures	Haoyi Yang et al.	arXiv	4
2026-10-19	2610.23841	StopWatch: Goal Grounding for Object-goal Navigation	Xinhao Liu et al.	arXiv	4
2026-10-19	2610.17644	DisaggKD: Efficient Knowledge Distillation through Teacher-Student Disaggregation and a Fused Loss	Ruixuan Tu et al.	arXiv	3
2026-10-19	2610.21482	AI-Driven Disaster Response and Displacement Monitoring	Noora Al-Emadi et al.	arXiv	3
2026-10-19	2610.21467	DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription	Wei Zeng et al.	arXiv	3
2026-10-19	2610.22343	GeoState: Learning View-Decoupled Geometry States for 3D World Modeling	Hongchang Liu et al.	arXiv	3
2026-10-19	2610.16763	Relational Learning as World Modeling	Zheyu Zhang et al.	arXiv	2
2026-10-19	2610.22306	ARC-SORT: Adaptive, Robust, Compensated Multi-Object Tracking with Interacting Multiple Models	Girish Kumar Adari	arXiv	2
2026-10-16	2610.22276	MJev-Spatial: System One Spatial Intelligence via Native Attention Matching	Luozheng Qin et al.	arXiv	87
2026-10-16	2610.22347	Speculative Forcing for Efficient Autoregressive Video Generation	Hyunwook Choi et al.	arXiv	80
2026-10-16	2610.22200	OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use	Hanzhang Zhou et al.	arXiv	77
2026-10-16	2610.18813	Self-Evolving Agent Harness	Chuyang Wei et al.	arXiv	76
2026-10-16	2610.17665	RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment	Qingchuan Ma et al.	arXiv	67
2026-10-16	2610.22174	Mosaic: Multi-Session Agentic Reinforcement Learning	Yilong Xu et al.	arXiv	64
2026-10-16	2610.18829	OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding	Xuyang Liu et al.	arXiv	64
2026-10-16	2610.22341	3DCodeVerse: Exploring 3D Worlds as Code	Yipeng Gao et al.	arXiv	62
2026-10-16	2610.22350	FDE-Gym: The Last Mile of AI Delivery	Dongxu Yang et al.	arXiv	58
2026-10-16	2610.20939	MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments	Panrong Tong et al.	arXiv	56
2026-10-16	2610.20818	Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation	Qian Yu et al.	arXiv	50
2026-10-16	2610.21601	Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation	Bingxi Hou et al.	arXiv	49
2026-10-16	2610.20693	Orbia: Do Generated Videos Form a Consistent 3D World?	Dongyue Lu et al.	arXiv	48
2026-10-16	2610.22264	SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation	Yufei Jiao et al.	arXiv	42
2026-10-16	2610.22194	AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning	Bingxiang He et al.	arXiv	42
2026-10-16	2610.12625	ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion	Zekai Gu et al.	arXiv	41
2026-10-16	2610.20603	CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation	Xiaoli Xu et al.	arXiv	40
2026-10-16	2610.21656	Data World: Scaling Data Environments from Scratch	Zhanli Li et al.	arXiv	39
2026-10-16	2610.20731	WorldCast: Exploring Intelligent Visual Generation in World State Prediction	Wenhao Yan et al.	arXiv	38
2026-10-16	2610.19849	DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding	Boyuan Sun et al.	arXiv	38
2026-10-16	2610.14993	Learning Where to Split: Dynamic Band Splitting for Audio Source Separation	Bingzhe Zhang et al.	arXiv	37
2026-10-16	2610.22192	Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine	Junyao Yang et al.	arXiv	37
2026-10-16	2610.21439	Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL	Skylar Zhai et al.	arXiv	36
2026-10-16	2610.22355	OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling	Bowei Liu et al.	arXiv	35
2026-10-16	2610.22311	Velox: Spatial Memory Makes World Models Efficient	Qiuhong Shen et al.	arXiv	35
2026-10-16	2610.16784	InfoVis: Unified Slide Image Generation and Editing	Jiahao Wang et al.	arXiv	32
2026-10-16	2610.22344	MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering	Shangheng Du et al.	arXiv	30
2026-10-16	2610.13781	SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models	Changhui Jing et al.	arXiv	30
2026-10-16	2610.17560	EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation	Zeru Shi et al.	arXiv	30
2026-10-16	2610.22282	Routing Policy Optimization for Online Diffusion Reinforcement Learning	Qiuhong Shen et al.	arXiv	29
2026-10-16	2610.20341	InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views	Yongzhen Hu et al.	arXiv	27
2026-10-16	2610.22131	Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling	Tong Zhu et al.	arXiv	27
2026-10-16	2610.21261	Behavioral Compositionality of Sparse Autoencoder Representations	Haotian Ma et al.	arXiv	25
2026-10-16	2610.21412	JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs	Kunlun Zhu et al.	arXiv	25
2026-10-16	2610.21463	Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents	Zilin Wang et al.	arXiv	24
2026-10-16	2610.21095	Can World and Action Modeling Benefit Each Other under Unified Causal Training?	Yue Su et al.	arXiv	23
2026-10-16	2610.17959	Virtual Head Attention	Xibo Ding et al.	arXiv	20
2026-10-16	2610.21306	VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models	Qi Lu et al.	arXiv	20
2026-10-16	2610.21359	SWE-at-Scale: Scalable Issue Synthesis from Historical Bug Fixes	Silin Chen et al.	arXiv	20
2026-10-16	2610.09695	Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?	Zihao Zhang et al.	arXiv	18
2026-10-16	2610.18461	MFVSR: A Multi-Style and Fine-Grained Benchmark for Video Subtitle Removal	Xiyan Huang et al.	arXiv	18
2026-10-16	2610.22352	SUPRA-TEX: 3D Generation with Super-Aligned Texture	Chen Yang et al.	arXiv	17
2026-10-16	2610.21055	Athanor: An Agent-Native System for Autonomous Post-Training Research	Yufa Zhou et al.	arXiv	16
2026-10-16	2610.17901	FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention	Guoxia Wang et al.	arXiv	15
2026-10-16	2610.22322	Learning Self-Orchestration in Decentralized Agent Swarms	Guowei Xu et al.	arXiv	15
2026-10-16	2610.16105	Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR	Daijiao Liu et al.	arXiv	14
2026-10-16	2610.17670	Cowork-Gym: Synthesizing Interactive Work Environments at Scale	Anni Zou et al.	arXiv	14
2026-10-16	2610.21453	CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance	Zixuan Wang et al.	arXiv	13
2026-10-16	2610.22217	Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models	Yuqi Xiong et al.	arXiv	13
2026-10-16	2610.22280	LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents	Qingni Wang et al.	arXiv	12
2026-10-16	2610.22362	CoDA: Co-Evolution of Data Engines and Action Policies	Tianjiao Yu et al.	arXiv	10
2026-10-16	2610.22070	Memory as Weights: Internalizing Long-Term History for Streaming Videos	Zhuoming Liu et al.	arXiv	10
2026-10-16	2610.19247	Copy-Paste Language Models	Nathan Godey et al.	arXiv	9
2026-10-16	2610.17113	Calibrated Typed Decisions for Entity, Relation, and Event Extraction	Yang Wang et al.	arXiv	9
2026-10-16	2610.21185	Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models	Kostas Triaridis et al.	arXiv	8
2026-10-16	2610.17697	LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification	Rodney Lafuente-Mercado et al.	arXiv	8
2026-10-16	2610.19397	SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning	Dingyi Rong et al.	arXiv	8
2026-10-16	2610.22371	Gen4P: Video Generators are 4D Perceivers	Yitong Xia et al.	arXiv	7
2026-10-16	2610.19063	WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models	Nan Zhou et al.	arXiv	7
2026-10-16	2610.15368	ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs	Yi Ge et al.	arXiv	7
2026-10-16	2610.22240	MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents	Huanyao Zhang et al.	arXiv	6
2026-10-16	2610.16397	Recursive Environment Scaling for General Long-Horizon Agents	Lingxiao Jing et al.	arXiv	6
2026-10-16	2610.06829	CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling	Yifan Zhang et al.	arXiv	6
2026-10-16	2610.22319	A team of Gemini 4 Argon agents beats Minecraft	Maxence Faldor et al.	arXiv	6
2026-10-16	2610.15924	Scalable Weak-to-Strong Verifier Hardening for Agent Environments	Chong Zeng et al.	arXiv	5
2026-10-16	2610.22358	PathFM: Fast Generative Forecasting of Multivariate Trajectories	Jiachen Yao et al.	arXiv	5
2026-10-16	2610.21025	Learning to Read Out: Unembedding Dynamics in Language Model Pretraining	Matteo He et al.	arXiv	5
2026-10-16	2610.20111	RepForcing: Representation-Space Initialization for Autoregressive Video Distillation	Siming Fu et al.	arXiv	5
2026-10-16	2610.19605	PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference	Gil Jae Song et al.	arXiv	5
2026-10-16	2610.22127	Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization	Sekh Mainul Islam et al.	arXiv	4
2026-10-16	2610.20993	One Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation	Hyunjong Ok et al.	arXiv	4
2026-10-16	2610.21500	When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill	Muhammad Ibrahim	arXiv	4
2026-10-16	2610.14232	Speech event detector: Timestamped detection of non-verbal vocalizations and background sounds for rich speech transcription	Ayush Kumar Bar et al.	arXiv	4
2026-10-16	2610.18125	H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression	Or Ronai et al.	arXiv	4
2026-10-16	2610.22186	EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment	Jiapeng Shi et al.	arXiv	4
2026-10-16	2610.19725	TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models	Haoxin Liu et al.	arXiv	4
2026-10-16	2610.20680	Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility	Sambit Ghosh et al.	arXiv	3
2026-10-16	2610.20461	Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR	Nguyen Nguyen et al.	arXiv	3
2026-10-16	2610.21910	CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness	Dongjie Cheng et al.	arXiv	3
2026-10-16	2610.18890	AI-Driven, Timing-Aware Power Optimization	Amit Sharma	arXiv	3
2026-10-16	2610.16355	PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation	Xinyu Guo et al.	arXiv	3
2026-10-16	2610.20509	VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution	Hairong Ni et al.	arXiv	3
2026-10-16	2610.06598	SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models	Xiaodong Wang et al.	arXiv	2
2026-10-16	2610.09016	PAIR: Bridging Perception and Action in Vision-Language-Action Models	Kaixi Feng et al.	arXiv	1
2026-10-15	2610.13521	Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation	Shi-Yu Tian et al.	arXiv	73
2026-10-15	2610.20399	Cortex: Consolidating Context into Parametric Memory	Jintian Zhang et al.	arXiv	70
2026-10-15	2610.20584	Player-1: Learning to Play from Synthetic Experience	Mingyu Ouyang et al.	arXiv	69
2026-10-15	2610.20571	Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation	Weijie Wang et al.	arXiv	68
2026-10-15	2610.19820	ActionOPD: Distilling Decisions, Not Tokens	Huining Yuan et al.	arXiv	59
2026-10-15	2610.19975	LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation	Zefeng He et al.	arXiv	56
2026-10-15	2610.19366	Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory	Minghao Guo et al.	arXiv	52
2026-10-15	2610.20344	Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents	Yuyao Ge et al.	arXiv	51
2026-10-15	2610.19789	More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning	Linhao Zhong et al.	arXiv	50
2026-10-15	2610.18072	LensErase: A Foundation Model for Erase Anything	Yunuo Chen et al.	arXiv	46
2026-10-15	2610.14448	KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization	Sihwan Park et al.	arXiv	40
2026-10-15	2610.20442	Towards Agentic Robots: Model, Data, Environment, and Harness	Chonghan Qin et al.	arXiv	38
2026-10-15	2610.18861	Hybrid Reasoning Agents	Jiaru Zou et al.	arXiv	37
2026-10-15	2610.19128	CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline	Yuxiang Lai et al.	arXiv	33
2026-10-15	2610.17309	StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions	Xialie Zhuang et al.	arXiv	31
2026-10-15	2610.19698	RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios	Chenhao Yuan et al.	arXiv	31
2026-10-15	2610.20572	Recovering Reliable Supervision via Critique-Guided On-Policy Distillation	Kaixiang Zhao et al.	arXiv	31
2026-10-15	2610.14270	The Thinking Leakage in Reinforcement Learning for LLMs	Wenxuan Zhu et al.	arXiv	29
2026-10-15	2610.02089	HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution	Kyochul Jang et al.	arXiv	29
2026-10-15	2610.13623	APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces	Ziyi Yang et al.	arXiv	25
2026-10-15	2610.20431	SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm	Qianru Meng et al.	arXiv	24
2026-10-15	2610.15542	Apertus 1.5: From Open Text Models to Open Multimodal Reasoners	Project Apertus et al.	arXiv	24
2026-10-15	2610.19560	τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions	Rishitosh Kumar Singh et al.	arXiv	23
2026-10-15	2610.18097	APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation	Sirui Zhang et al.	arXiv	23
2026-10-15	2610.04781	Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate	Wanzhou Lei et al.	arXiv	21
2026-10-15	2610.19118	DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision	Yifan Lan et al.	arXiv	20
2026-10-15	2610.14162	Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation	Hermann Kumbong et al.	arXiv	19
2026-10-15	2610.19729	A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics	Hao-Jen Chien et al.	arXiv	19
2026-10-15	2610.20256	Long-Horizon RL Needs Muon	Kai Ruan et al.	arXiv	19
2026-10-15	2610.15715	History Replays Itself: Unleashing Long-Context Capability in Linear Attention	Li Nanbo et al.	arXiv	17
2026-10-15	2610.18248	Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models	Guoming Ling et al.	arXiv	15
2026-10-15	2610.17191	FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation	Zekun Shi et al.	arXiv	14
2026-10-15	2610.14020	LabInstruct: Benchmarking Situated Instructional Video Generation for Lab Procedures	Yuming Fu et al.	arXiv	14
2026-10-15	2610.14774	ProgAgent: Learning Tool Orchestration through Programmatic Training	Hao Li et al.	arXiv	14
2026-10-15	2610.18284	Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation	Yaoli Liu et al.	arXiv	14
2026-10-15	2610.16302	RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models	Yaoyang Liu et al.	arXiv	14
2026-10-15	2610.19628	Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching	Zeyang Zhang et al.	arXiv	13
2026-10-15	2610.19026	Joint Subspace Sparse Attention for Efficient Long-Context Decoding	Jiwon Song et al.	arXiv	13
2026-10-15	2610.17771	Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders	Xin Li et al.	arXiv	13
2026-10-15	2610.15725	SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification	Alan Tang et al.	arXiv	13
2026-10-15	2610.19100	GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning	Qingsong Xie et al.	arXiv	13
2026-10-15	2610.20195	What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds	Caixin Kang et al.	arXiv	12
2026-10-15	2610.20609	SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving	Shaoyuan Xie et al.	arXiv	11
2026-10-15	2610.17246	LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators	Riccardo De Santi et al.	arXiv	10
2026-10-15	2610.18755	PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards	Yunkai Zhan et al.	arXiv	9
2026-10-15	2610.17016	ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty	Yuyang Dai et al.	arXiv	9
2026-10-15	2610.19525	Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following	Sangyeon Yoon et al.	arXiv	9
2026-10-15	2610.20828	CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation	Zinan Tang et al.	arXiv	7
2026-10-15	2610.18598	Rethinking Projector Training in Multimodal LLMs	Fabian Gröger et al.	arXiv	7
2026-10-15	2610.20220	Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance	Zhuobai Dong et al.	arXiv	7
2026-10-15	2610.14261	BigCell: Generating Gigapixel Whole-Slide Images	Srikar Yellapragada et al.	arXiv	7
2026-10-15	2610.20604	VITAL: From Visual Motion to Precise Action	Ao Liang et al.	arXiv	7
2026-10-15	2610.19121	Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming	Woosang Lim et al.	arXiv	6
2026-10-15	2610.17242	When Left Is Right? Camera-Motion Understanding beyond Screen	Chong Cheng et al.	arXiv	6
2026-10-15	2610.19420	From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents	Yue Zhang et al.	arXiv	6
2026-10-15	2610.17638	Acting Through Registers	Yiwei Zhang et al.	arXiv	6
2026-10-15	2610.20456	The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation	Ian Magnusson et al.	arXiv	6
2026-10-15	2610.20586	Continuum Attention	Afshin Khadangi	arXiv	6
2026-10-15	2610.20516	VASPO: Self-Distillation with Privileged Value Estimation	Fei Wu et al.	arXiv	5
2026-10-15	2610.19696	Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models	Xin Li et al.	arXiv	5
2026-10-15	2610.20582	Latent Compaction with Test-Time Training	Yingfa Chen et al.	arXiv	5
2026-10-15	2610.19551	TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering	Yiyang Chen et al.	arXiv	5
2026-10-15	2610.19138	MA-Bench: Measuring Operational Planning in Language Models	Rodney Lafuente-Mercado et al.	arXiv	5
2026-10-15	2610.17893	Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards	Keru Chen et al.	arXiv	5
2026-10-15	2610.14216	Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules	Samuele Giampieri	arXiv	4
2026-10-15	2610.17301	The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow	Arya Fayyazi et al.	arXiv	4
2026-10-15	2610.17079	Rethinking LLM-Guided Visual Question Answering: Does Deeper Knowledge Integration Really Help?	Aneerban Saha et al.	arXiv	4
2026-10-15	2610.19726	Generative World Simulation with DAO and JING	XGEN Team et al.	arXiv	4
2026-10-15	2610.16338	SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation	Kaisi Guan et al.	arXiv	4
2026-10-15	2610.14096	SWEeper-Bench: Can Agents Discover Bugs in Interactive Software?	Yang Yao et al.	arXiv	4
2026-10-15	2610.17831	Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing	Xiaolong Xu et al.	arXiv	4
2026-10-15	2610.15425	Exploring the Limits of Combinatorial Generalization in Embodied Manipulation	Xupeng Zhang et al.	arXiv	4
2026-10-15	2610.20526	Lluna: Collaborative Unimodal Models for Missing-Modality Inference	Haoyue Bai et al.	arXiv	3
2026-10-15	2610.18762	Looking Complete Is Not Being Grounded: Evaluating LLM Sitreps Against Human-Authored Situation Reports	Sachin Kumar	arXiv	3
2026-10-15	2610.19361	VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement	Kyusong Lee et al.	arXiv	3
2026-10-15	2610.18354	Choosing LLMs for Strategic Agent Interactions	Arastun Mammadli et al.	arXiv	3
2026-10-15	2610.20588	Your Transformer Is Secretly Elastic	Walter Simoncini et al.	arXiv	3
2026-10-15	2610.18638	To Align or Not To Align: Check Your COMPASS Before You Train	Fabian Gröger et al.	arXiv	3
2026-10-15	2610.19422	AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety	Chenxu Wang et al.	arXiv	3
2026-10-15	2610.13239	Jag: Direct Box Prediction for Efficient Visual Grounding	Xiuyuan Zhu et al.	arXiv	3
2026-10-15	2610.18838	Scaling Online Optimal Transport Minibatches for Flow Matching	Peter Chen et al.	arXiv	3
2026-10-15	2610.10787	NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime	Gengze Zhou et al.	arXiv	3
2026-10-15	2610.09055	MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking	Shuaijun Liu et al.	arXiv	3
2026-10-15	2610.20524	Physical Time as a Missing Dimension of Robot Policy Memory Dynamics	Yushen Liang et al.	arXiv	3
2026-10-15	2606.24472	G^3VLA: Geometric Inductive Bias for Vision-Language-Action Models	Yue Peng et al.	arXiv	3
2026-10-15	2610.20137	StreamErase: Towards Ultra-Fast Streaming Video Erasing	Zhuobai Dong et al.	arXiv	2
2026-10-15	2610.15112	Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving	Tianyi Yang et al.	arXiv	1
2026-10-15	2610.05230	Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization	Yifan Li et al.	arXiv	1
2026-10-14	2610.18773	Jeva: System One Models from First Principles	Qi Li et al.	arXiv	180
2026-10-14	2610.18356	Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes	Yu Wang et al.	arXiv	130
2026-10-14	2610.18615	VideoJev: System One Model for Video Understanding and Interaction	Yuhan Zhu et al.	arXiv	102
2026-10-14	2610.18774	GreenWAM: A World Foundation Model for Robotics	Gennady Sidorov et al.	arXiv	98
2026-10-14	2610.16794	TPPO: Tracking-Value PPO For Language Model Reasoning	Futing Wang et al.	arXiv	90
2026-10-14	2610.14709	Vela: User Behavior as Supervision Sparks LLM Intelligence	Yang Xiao et al.	arXiv	85
2026-10-14	2610.14224	Harness^2: Recursive Agent Harnessing for an Open World	Ruiyao Xu et al.	arXiv	84
2026-10-14	2610.13990	DoSA: Dots Sparse Attention	Fanxu Meng et al.	arXiv	73
2026-10-14	2610.15028	UltraBERT: Beyond the Limit of BERT Pre-Training	Jungwoo Park et al.	arXiv	68
2026-10-14	2610.17201	Multics: Generative Multi-Player World Model with Hierarchical Communication	Kaiyi Huang et al.	arXiv	65
2026-10-14	2610.01496	SALD: Self-Referenced Advantage Learning for Diffusion Models	Aryan Das et al.	arXiv	64
2026-10-14	2610.15166	ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling	Xinge Peng et al.	arXiv	62
2026-10-14	2610.18868	Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards	Wenbo Hu et al.	arXiv	53
2026-10-14	2610.14609	EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment	ZiAn Wang et al.	arXiv	51
2026-10-14	2610.17227	AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers	Javad Rajabi et al.	arXiv	51
2026-10-14	2610.12843	APEX: Asynchronous Prefix Denoising for Extreme Compression	David Dinkevich et al.	arXiv	50
2026-10-14	2610.17953	Agent-Reflex: Teaching Language Agents to Act Reflectively	Guanting Dong et al.	arXiv	47
2026-10-14	2610.18860	AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards	Xin Gao et al.	arXiv	43
2026-10-14	2610.17928	Learning How to Remember: Memory Modality Selection for GUI Agents	Taeyun Roh et al.	arXiv	40
2026-10-14	2610.18067	WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution	Hang He et al.	arXiv	40
2026-10-14	2610.18568	WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction	Haomin Wang et al.	arXiv	38
2026-10-14	2610.11850	VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval	Shahaf Wagner et al.	arXiv	37
2026-10-14	2610.18272	JevGPT: Thinking Fast and Slow in Autonomous Research	Yasheng Sun et al.	arXiv	37
2026-10-14	2610.16811	X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning	Yi Wang et al.	arXiv	34
2026-10-14	2610.14118	ClawLoop: Self-Improving Agents via Harness-Native Training Loop	Hansi Yang et al.	arXiv	33
2026-10-14	2610.16354	Self-Distillation with Verbal Regularization	Jiazheng Li et al.	arXiv	32
2026-10-14	2610.17552	FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching	Ruchang Yao et al.	arXiv	30
2026-10-14	2610.12818	LeWAM: End-to-End World and Action Modeling with JEPAs	Minghao Fu et al.	arXiv	30
2026-10-14	2610.15765	A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution	Alan Wu et al.	arXiv	29
2026-10-14	2610.16577	CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction	Jialei Wang et al.	arXiv	29
2026-10-14	2610.18472	Simplifying and Improving On-Policy Distillation for Few-Step Diffusion	Jiawei Zhang et al.	arXiv	27
2026-10-14	2610.15782	Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping	Songze Li et al.	arXiv	27
2026-10-14	2610.17666	DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter	Xuyan Ye et al.	arXiv	27
2026-10-14	2610.14091	Pristine Models	Anirudh Sundara Rajan et al.	arXiv	26
2026-10-14	2610.18484	ReTerm: Recovery Training for Self-Improving Terminal Agents	Wei Xie et al.	arXiv	26
2026-10-14	2610.18010	Fish Audio Drama 3 Technical Report	Dawei Han et al.	arXiv	26
2026-10-14	2610.18871	Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion	Chih-Hai Su et al.	arXiv	25
2026-10-14	2610.17656	Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence	Jiahao Meng et al.	arXiv	24
2026-10-14	2610.18872	EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ	Yunsong Zhou et al.	arXiv	24
2026-10-14	2610.15915	VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It	Binxiao Xu et al.	arXiv	23
2026-10-14	2610.14293	GeoFix: Geometry Fixing for 4D Consistent Generation	Yeobin Hong et al.	arXiv	23
2026-10-14	2610.14766	Last Secure Code Benchmark: Is the Code You Vibe Secure?	Tianyi Wu et al.	arXiv	21
2026-10-14	2602.05758	LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards	Qize Yu et al.	arXiv	21
2026-10-14	2610.14228	Latent World Action Model for GUI Agents	Seungjun Yu et al.	arXiv	21
2026-10-14	2610.18596	ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models	Changyeon Kim et al.	arXiv	20
2026-10-14	2610.16118	Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding	Shuo Gao et al.	arXiv	19
2026-10-14	2609.38847	Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics	Maoqi Liu et al.	arXiv	18
2026-10-14	2610.18092	LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity	Yibo Wang et al.	arXiv	17
2026-10-14	2609.38377	PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos	Max Ku et al.	arXiv	15
2026-10-14	2610.18206	SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents	Do Xuan Trong et al.	arXiv	14
2026-10-14	2610.14351	Learning Transferable World-Action Models from Task-Paired Human Videos	Jeongeun Park et al.	arXiv	12
2026-10-14	2610.15035	What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training Strategies	Duo Li et al.	arXiv	12
2026-10-14	2610.14163	AutoEnvScaling: Automating the Data Flywheel with Terminal Agents	Simon Yu et al.	arXiv	11
2026-10-14	2610.16135	Omni-Modal LLMs Know More Than They Say	Na Min An et al.	arXiv	10
2026-10-14	2610.08432	EMHO: EMbodied Agent Harness Optimization via Experience Traces	Hyun Jung Lee et al.	arXiv	10
2026-10-14	2610.18579	Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops	Yubo Li et al.	arXiv	9
2026-10-14	2610.13989	PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems	Chong Zhang et al.	arXiv	9
2026-10-14	2610.15327	CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks	Mengzhe Geng et al.	arXiv	9
2026-10-14	2610.16533	Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards	Zhipeng Chen et al.	arXiv	9
2026-10-14	2610.14726	LightVAE: Towards Compact and Efficient Video Autoencoders	Shiqiao Gu et al.	arXiv	8
2026-10-14	2610.18846	WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World	Mengchen Zhang et al.	arXiv	8
2026-10-14	2610.18766	Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges	Tianci Liu et al.	arXiv	8
2026-10-14	2610.10808	Controlled Acquisition and Abstention in Three-Channel Score Conflicts	Mengzhe Geng	arXiv	8
2026-10-14	2610.15208	PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces	M. Yigit Turali et al.	arXiv	8
2026-10-14	2610.15772	RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution	Fan Zhang et al.	arXiv	7
2026-10-14	2610.16117	Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues	Chen Huang et al.	arXiv	6
2026-10-14	2610.18760	Beyond the Verdict: Agentic Code Judging with Verifiable Feedback	Zheye Deng et al.	arXiv	6
2026-10-14	2610.18614	Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents	Ashutosh Hathidara	arXiv	6
2026-10-14	2610.14158	Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability	Kuan Zhang et al.	arXiv	6
2026-10-14	2610.16361	HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision	Iman Barati et al.	arXiv	6
2026-10-14	2610.13416	Web$hell: A Unified Interface for Agentic Web Access	Sunghwan Kim et al.	arXiv	6
2026-10-14	2610.15788	Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams	Yirui Qi et al.	arXiv	6
2026-10-14	2610.18497	Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments	Linhai Ma et al.	arXiv	5
2026-10-14	2610.04906	Scaling Verifiable Environments for Long-horizon Work Agents	Jiazheng Zhang et al.	arXiv	5
2026-10-14	2610.16601	MixLID: Token-Level Language Identification in Mixed-Language Text	Seongtae Hong et al.	arXiv	5
2026-10-14	2610.18862	DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning	Minghao Luo et al.	arXiv	5
2026-10-14	2610.00359	Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength	Candi Zheng et al.	arXiv	5
2026-10-14	2610.16759	Image Tokenizers Should Be Trained Between Images	Ole Beißwenger et al.	arXiv	4
2026-10-14	2610.15965	Scaling Repeated-Data Pretraining: Batch Size, Regularization, and GPU-Time Tradeoffs	Sewon Min	arXiv	4
2026-10-14	2610.12412	WorldCast: Distributed Multiplayer World Models	Ziyang Ye et al.	arXiv	4
2026-10-14	2610.16985	AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding	Yuqi Ye et al.	arXiv	4
2026-10-14	2610.17625	4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling	Jianhui Zhang et al.	arXiv	4
2026-10-14	2610.17540	TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency	Jack Lu et al.	arXiv	4
2026-10-14	2610.15357	UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space	Wenjue Chen et al.	arXiv	4
2026-10-14	2610.15124	ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer	Can Jin et al.	arXiv	4
2026-10-14	2610.18677	Model-Based Online Decision Making via Generative Trajectory Planning	Haldun Balim et al.	arXiv	3
2026-10-14	2610.15228	Words to World: Benchmarking LLMs in Interactive Physical Environments	Xinnan Dai et al.	arXiv	3
2026-10-14	2610.18738	Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization	Hao Bai et al.	arXiv	3
2026-10-14	2610.16172	EventLens: Event-Structure Reinforcement Learning for Video Understanding	Guowen Zhang et al.	arXiv	3
2026-10-14	2609.37377	Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation	Jiaxuan Wang et al.	arXiv	3
2026-10-14	2610.18025	SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces	Harshit Joshi et al.	arXiv	3
2026-10-14	2610.14912	Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents	Mantas Lukauskas et al.	arXiv	3
2026-10-14	2610.04851	CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery	Tao Feng et al.	arXiv	3
2026-10-14	2610.02638	Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript	Jie Jin et al.	arXiv	2
2026-10-14	2610.14530	Who to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation	Ruiyang Wang et al.	arXiv	2
2026-10-14	2607.08809	Privacy-Preserving Intent Fulfilment and Assurance for 6G RAN	Joss Armstrong	arXiv	1
2026-10-14	2610.18352	Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation	Youpeng Wen et al.	arXiv	1
2026-10-13	2610.13166	Scaling Agentic Data for Long-Horizon Terminal Intelligence	Shun Zou et al.	arXiv	140
2026-10-13	2609.39601	GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives	Qize Yu et al.	arXiv	123
2026-10-13	2610.13361	AgentSWE: Can Coding Agents Build the Agent You Actually Want?	Jiahao Wang et al.	arXiv	84
2026-10-13	2610.11765	Thinking Inertia: LLMs Keep Thinking When Told Not To	Dianqiao Lei et al.	arXiv	70
2026-10-13	2610.13630	Multi-Stream Attention Residuals	Xiaohan Qin et al.	arXiv	51
2026-10-13	2609.39600	GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed	Qize Yu et al.	arXiv	47
2026-10-13	2610.09326	VIS-Ground: Video Interactive Storytelling with Contextual Grounding	Bingxuan Li et al.	arXiv	43
2026-10-13	2609.36642	PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning	Muyang Li et al.	arXiv	40
2026-10-13	2609.36616	CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation	Hanwen Lu et al.	arXiv	30
2026-10-13	2610.13832	SpatialASM: Internalizing Active Mentalization for Spatial Reasoning	Yuhong Liu et al.	arXiv	30
2026-10-13	2609.35291	Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment	Shunchang Liu et al.	arXiv	27
2026-10-13	2609.33304	Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents	Fuyao Zhang et al.	arXiv	24
2026-10-13	2610.12417	WOVEN: Weaving Visual World Modeling into Multimodal LLMs	Zheyu Fan et al.	arXiv	18
2026-10-13	2610.03308	T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images	Atsuhiro Noguchi et al.	arXiv	16
2026-10-13	2610.12933	Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training	Suorong Yang et al.	arXiv	14
2026-10-13	2610.09396	ARCS: Towards Precise Text-to-SQL via Structured Disambiguation	Yihao Hu et al.	arXiv	12
2026-10-13	2610.05637	Visual Grounding Safety in Vision-Language Models	Erfan Shayegani et al.	arXiv	11
2026-10-13	2610.09116	SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code	Seemandhar Jain et al.	arXiv	11
2026-10-13	2610.12998	Evaluating LLM Creativity through Long-Tail Performance	Yichen Wang et al.	arXiv	10
2026-10-13	2609.35965	Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method	Yunzhe Xu et al.	arXiv	10
2026-10-13	2610.02740	Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps	Jiaxin Zhang et al.	arXiv	9
2026-10-13	2610.13481	Branching On-Policy Distillation	Dongyang Chen et al.	arXiv	9
2026-10-13	2610.03039	HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning	Donggyun Kim et al.	arXiv	7
2026-10-13	2610.12099	UNITAS: A 3D-Native World Action Model for Embodied Manipulation	Ruixiang Wang et al.	arXiv	7
2026-10-13	2610.00707	Initialization Improves LLM-Driven Discovery	Mansi Sakarvadia et al.	arXiv	7
2026-10-13	2610.03825	Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score	Parth Kulshreshtha et al.	arXiv	4
2026-10-12	2610.12572	DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models	Zhenglin Wan et al.	arXiv	103
2026-10-12	2610.12611	SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments	Tian Jin et al.	arXiv	86
2026-10-12	2610.07987	VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs	Yuan Feng et al.	arXiv	61
2026-10-12	2610.13527	S-Space: Exploring Spatial Workspace in Multimodal Language Models	Zhiyuan Shi et al.	arXiv	58
2026-10-12	2609.38748	Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation	Hanmo Chen et al.	arXiv	58
2026-10-12	2610.12772	Reflex: Visually Grounded Reactive Humanoid Control	Taoyang Jia et al.	arXiv	57
2026-10-12	2610.13912	RSI-Anything: Unlocking Recursive Self-Improvement with World Models	Taoyong Cui et al.	arXiv	45
2026-10-12	2610.13395	ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents	Chengyi Yang et al.	arXiv	45
2026-10-12	2610.12984	Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction	Yuqi Huang et al.	arXiv	43
2026-10-12	2610.13021	EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents	Jie Huang et al.	arXiv	43
2026-10-12	2610.13113	Continually Post-training Small Models via Synthetic Self-distillation	Woosung Koh et al.	arXiv	39
2026-10-12	2610.11361	SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model	Aviad Dahan et al.	arXiv	39
2026-10-12	2610.12341	Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition	Kaisen Yang et al.	arXiv	32
2026-10-12	2610.12570	Contextual Correction of Parallel Drafts for Speculative Decoding	Roy Eisenstadt et al.	arXiv	31
2026-10-12	2609.37712	PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence	GuangJian Team et al.	arXiv	31
2026-10-12	2610.07121	SoloQ: Calibration-Free Quantization for Diffusion Language Models	Donghyun Lee et al.	arXiv	30
2026-10-12	2610.11291	When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better	Siyan Zhao et al.	arXiv	28
2026-10-12	2610.05014	MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code	Xueyi Chen et al.	arXiv	23
2026-10-12	2610.07625	Stateless Language Agents: Scaling Long-Horizon Automated Research	Qizheng Zhang et al.	arXiv	23
2026-10-12	2610.12978	Learning Representations to Guide Pixel Diffusion Transformers	Zihao Pan et al.	arXiv	23
2026-10-12	2610.12114	Universal Textual Teaching for LLMs	Zhanyi Lu et al.	arXiv	18
2026-10-12	2610.12668	Recurrent Harness for Agentic Continual Learning	Yuxin Xiao et al.	arXiv	17
2026-10-12	2610.13944	InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators	Xuanlang Dai et al.	arXiv	17
2026-10-12	2610.09788	Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression	Mingqing Yuan et al.	arXiv	17
2026-10-12	2610.12582	One Model to Loop Them All: Elastic Latent Recurrence for Language Models	Faisal Ladhak et al.	arXiv	16
2026-10-12	2610.09633	Coding-Agent Benchmarks Should Match Their Users' Task Flows	Igor Slinko et al.	arXiv	15
2026-10-12	2609.36641	Inducing Process Supervision from Outcome-Only Reinforcement Learning	Shengda Fan et al.	arXiv	14
2026-10-12	2610.13947	Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark	Xudong Cai et al.	arXiv	14
2026-10-12	2610.10288	TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning	Dayou Li et al.	arXiv	13
2026-10-12	2610.12569	SWE-Duel: Towards a Self-Scaling Arena for Coding Agents	Wei Minn et al.	arXiv	13
2026-10-12	2610.08966	Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models	Xingang Guo et al.	arXiv	12
2026-10-12	2610.10893	Less from More: Reinforcing Sparse Video Reasoning from Dense References	Wenfang Sun et al.	arXiv	12
2026-10-12	2610.13118	The value of information and the emergence of communication in evolved e-puck robots	Fernando Montes-Gonzalez	arXiv	11
2026-10-12	2609.36760	QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching	Zunhai Su et al.	arXiv	10
2026-10-12	2610.07207	Distributionally Robust Mixture-of-Experts Training	Xin Teng et al.	arXiv	9
2026-10-12	2610.12939	Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding	Raghavv Goel et al.	arXiv	9
2026-10-12	2609.39566	From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning	Minye Shao et al.	arXiv	9
2026-10-12	2610.06354	GraphDecisionBench: Benchmarking System One Models on Graph Tasks	Xianliang Yang et al.	arXiv	9
2026-10-12	2610.12307	BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion	Ozgur Kara et al.	arXiv	8
2026-10-12	2610.00423	The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation	S. Aaron McClendon et al.	arXiv	8
2026-10-12	2610.11993	DataVista: Diagnosing Multimodal LLMs on Data Video Understanding	Yupeng Xie et al.	arXiv	8
2026-10-12	2610.12453	Mental-Models for Multi-Agent Systems	Hanan Gani et al.	arXiv	7
2026-10-12	2610.13316	ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning	Armando Fortes et al.	arXiv	7
2026-10-12	2610.13171	PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling	Nan Jiang et al.	arXiv	7
2026-10-12	2610.00898	When Do Biological Reasoning Models Use Their Biological Inputs?	Ada Fang et al.	arXiv	7
2026-10-12	2610.13181	MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement	Chenge Li et al.	arXiv	7
2026-10-12	2609.37950	Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution	Bingjun Luo et al.	arXiv	7
2026-10-12	2610.13205	Rethinking Relative Policy Differences Transfer of On-Policy Distillation	Rong Wu et al.	arXiv	7
2026-10-12	2610.12602	Self-Preservation in Language Models	Dongkyu Cho et al.	arXiv	5
2026-10-12	2610.09607	Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning	HyeonSeok Lim et al.	arXiv	5
2026-10-12	2610.13627	AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis	Natapong Nitarach et al.	arXiv	5
2026-10-12	2610.11069	Clinician use of language models diverges from how the models are evaluated	Krithik Vishwanath et al.	arXiv	4
2026-10-12	2609.37359	Encore: Few-Shot Agentic Discovery of Manipulation Strategies	Yifan Kang et al.	arXiv	4
2026-10-12	2610.12102	Few-Step Generation via Data-Space Iteration	Shanchuan Lin et al.	arXiv	3
2026-10-12	2609.39635	SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations	Shuang Liang et al.	arXiv	3
2026-10-12	2610.07018	When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models	Ziquan Zhu et al.	arXiv	3
2026-10-12	2610.10512	Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery	Chen Xu et al.	arXiv	2
2026-10-12	2610.11215	GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images	Qirui Wu et al.	arXiv	2
2026-10-12	2610.12416	MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances	Mingyuan Lei et al.	arXiv	2
2026-10-12	2610.12470	Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration	Jusuk Lee et al.	arXiv	2
2026-10-09	2610.12242	TokenRouter: Efficient Serving System for Token-Level LLM Routing	Tianyu Fu et al.	arXiv	127
2026-10-09	2610.11959	MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement	Core Team et al.	arXiv	87
2026-10-09	2610.12126	SuperNav: An Agentic Navigation System for Any Task in Any Scene	Jinkai Zhang et al.	arXiv	84
2026-10-09	2610.12374	AgentGarten: Code Worlds for Evolving Agents	Jiawei Chi et al.	arXiv	72
2026-10-09	2610.12299	Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction	Dahyun Chung et al.	arXiv	61
2026-10-09	2610.12461	OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs	You-Zhe Xie et al.	arXiv	60
2026-10-09	2609.38173	In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks	Minxing Li et al.	arXiv	57
2026-10-09	2610.08215	Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?	Yibo Li et al.	arXiv	55
2026-10-09	2610.11287	REMORY: Learning Residual Memory for Context Compaction	Hanchen Xia et al.	arXiv	54
2026-10-09	2610.06100	From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation	Quanyu Long et al.	arXiv	54
2026-10-09	2610.09087	U-Space: Uncovering When and Why Uncertainty Arises in Language Models	Tobias Braun et al.	arXiv	47
2026-10-09	2610.12468	DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training	Junyan Li et al.	arXiv	46
2026-10-09	2610.11794	Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks	Haoyu Zhao et al.	arXiv	43
2026-10-09	2610.06801	MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers	Jiarui Chen et al.	arXiv	40
2026-10-09	2610.12442	LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation	Suhwan Cho et al.	arXiv	38
2026-10-09	2610.02967	Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards	Yuanhao Ban et al.	arXiv	36
2026-10-09	2610.12289	TestPrism: Rethinking Test Evaluation Beyond a Single Reference	Han Li et al.	arXiv	35
2026-10-09	2610.12327	SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference	Qitong Wang et al.	arXiv	31
2026-10-09	2501.09223	Foundations of Large Language Models	Tong Xiao et al.	arXiv	29
2026-10-09	2610.12369	Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement	Kairui Hu et al.	arXiv	25
2026-10-09	2610.06406	What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents	Zhongxiang Sun et al.	arXiv	24
2026-10-09	2610.12419	OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video	Hongyu Li et al.	arXiv	23
2026-10-09	2606.03335	A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning	Rui Zhang et al.	arXiv	22
2026-10-09	2610.12229	VibeEdit: Image Editing with Canvas Instructions	Jinjing Zhao et al.	arXiv	20
2026-10-09	2610.11816	Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers	Yubo Sun et al.	arXiv	20
2026-10-09	2609.39068	SparseEngine: Sparse-First Inference Engine	Jitai Hao et al.	arXiv	19
2026-10-09	2610.12343	Reasoning-Informed Visual Editing	Xue Yang et al.	arXiv	19
2026-10-09	2610.07730	SanSi: A Looped Typed Decision Model for System 1.5 Thinking	Shuyu Gan et al.	arXiv	19
2026-10-09	2610.12459	WorldGuide: Goal-Directed Video World Model for Procedural Task Execution	Ankan Deria et al.	arXiv	18
2026-10-09	2610.11322	USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation	Chuanrui Zhang et al.	arXiv	17
2026-10-09	2610.12423	Pumpire: Unified Benchmark for Metric Distance Estimation	Siyu Chen et al.	arXiv	16
2026-10-09	2610.12458	OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning	Zhongyu Yang et al.	arXiv	15
2026-10-09	2610.11366	SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces	Rongxue Li et al.	arXiv	15
2026-10-09	2610.12403	ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills	Hongxing Li et al.	arXiv	14
2026-10-09	2609.33987	Opera: A Verbal Critic Framework for Long-horizon Coding Agents	Kai Mei et al.	arXiv	13
2026-10-09	2610.12421	Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching	Luping Liu et al.	arXiv	13
2026-10-09	2609.35433	ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning	Yihang Chen et al.	arXiv	13
2026-10-09	2610.04977	Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation	Jerry Wang et al.	arXiv	13
2026-10-09	2610.12230	From Prompting to Composing: A Spatial Canvas Interface for Poster Generation	Yitong Wang et al.	arXiv	13
2026-10-09	2610.03858	Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks	Maximilian Schlegel et al.	arXiv	12
2026-10-09	2610.11251	V-CoLA: Vision Token Compression with Linear Attention	Hao Jiang et al.	arXiv	12
2026-10-09	2610.12183	A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization	Ming Chen et al.	arXiv	11
2026-10-09	2610.12452	BrickBench: Evaluating Agentic Brick Design	Peter Kulits et al.	arXiv	11
2026-10-09	2610.12402	SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models	Hongxing Li et al.	arXiv	11
2026-10-09	2610.12360	Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict	Kaiser Sun et al.	arXiv	10
2026-10-09	2610.08927	Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station	Wenyu Du et al.	arXiv	9
2026-10-09	2610.12399	SpaceFlow: Locally Controllable 3D Generation	Neil De La Fuente et al.	arXiv	9
2026-10-09	2610.12448	One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts	Adrian Bulat et al.	arXiv	8
2026-10-09	2609.35855	Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution	Yubin Lyu et al.	arXiv	7
2026-10-09	2610.12355	Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models	Hongxing Li et al.	arXiv	7
2026-10-09	2610.06496	You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue	Junle Chen et al.	arXiv	6
2026-10-09	2610.11570	Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals	Pengxiang Li et al.	arXiv	6
2026-10-09	2610.11169	Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub	Fahd Seddik	arXiv	4
2026-10-09	2610.10549	Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction	Yipeng Li et al.	arXiv	4
2026-10-09	2610.10355	MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent	Zekai Liu et al.	arXiv	4
2026-10-09	2610.11566	Incremental Open-Ended Deep Research with Structured Harness	Meilin Chen et al.	arXiv	4
2026-10-09	2610.03136	Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation	Oliver Hauck et al.	arXiv	4
2026-10-09	2610.08917	CARE: Certifying Acceleration for Vision-Language-Action Inference	Rui Liu et al.	arXiv	4
2026-10-09	2609.34344	Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors	Yuchen Cai et al.	arXiv	4
2026-10-09	2610.09639	On-Policy Distillation Teaches New Skills but Not New Knowledge	Yixuan Tang et al.	arXiv	4
2026-10-09	2610.11216	The Lattice of Transition Laws	T. Y. Tsui et al.	arXiv	3
2026-10-09	2610.09146	Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI	Yexiao He et al.	arXiv	3
2026-10-09	2610.04875	SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models	Chung-En Ho et al.	arXiv	3
2026-10-09	2610.09059	EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks	Sai Karthik Navuluru et al.	arXiv	3
2026-10-09	2610.08941	SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation	Yunheng Liu et al.	arXiv	3
2026-10-09	2610.11975	Predicting Cable Dynamics with Physical Attention Bias	Avihai Giuili et al.	arXiv	2
2026-10-09	2610.08585	Incidental information contaminates patient notes and disrupts clinical reasoning in large language models	Krithik Vishwanath et al.	arXiv	2
2026-10-09	2605.22949	MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination	Joss Armstrong	arXiv	2
2026-10-09	2609.38527	Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics	Fernando Montes-Gonzalez	arXiv	1
2026-10-09	2610.09280	Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation	Fernando Montes-Gonzalez	arXiv	1
2026-10-09	2609.31507	SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery	Jiajun Jiang et al.	arXiv	1
2026-10-09	2610.02959	TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows	Shuai Fu et al.	arXiv	1
2026-10-08	2610.08077	Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight	Haoxiang Zhang et al.	arXiv	172
2026-10-08	2610.08699	nanoMuse: An Open-Source Personal Agent for Every Device You Own	Guangyi Liu et al.	arXiv	102
2026-10-08	2610.10528	Long-WAM: Scaling the Context of World-Action Models	Wei Huang et al.	arXiv	97
2026-10-08	2610.02054	UniWAM: Unified World-Action Model	Jiayi Chen et al.	arXiv	77
2026-10-08	2610.08621	Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness	Jiajun Chen et al.	arXiv	74
2026-10-08	2610.10524	GRACE: Generation-aware latent compression for efficient video generation	Jiyoung Kim et al.	arXiv	73
2026-10-08	2610.02368	Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation	Shukai Gong et al.	arXiv	69
2026-10-08	2610.04299	Questioning the Questions: Sustaining Self-Evolution in Reasoning Models	Jinyuan Li et al.	arXiv	55
2026-10-08	2610.10539	Tetris3D: 3D Scene Generation With Objects That Fit Together	Jaeyeong Kim et al.	arXiv	48
2026-10-08	2610.07967	DecepEval: A Benchmark for Evaluating Deception in LLM Agents	Yiming Xu et al.	arXiv	47
2026-10-08	2610.10429	SGF+: Decoupling Gradient Flows for Autoregressive Video Generation	Zihan Su et al.	arXiv	46
2026-10-08	2610.10444	RunningTab: Direct Workspace Interaction with Environment-Side Tabs	Jinheon Baek et al.	arXiv	43
2026-10-08	2609.38169	STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization	Bingchen Yao et al.	arXiv	42
2026-10-08	2610.10409	RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments	Zhiqin Yang et al.	arXiv	39
2026-10-08	2610.09823	UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation	Deyuan Liu et al.	arXiv	37
2026-10-08	2610.08995	PhysEvo: Astra Can Act, Let It	Wenqing Tian et al.	arXiv	33
2026-10-08	2609.33678	SWE-Game: Can Coding Agents Build the Games We Want?	Xiaoyu Chen et al.	arXiv	33
2026-10-08	2610.03185	Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective	Han Cui et al.	arXiv	30
2026-10-08	2609.39306	ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation	Shengjie Jin et al.	arXiv	30
2026-10-08	2610.09450	Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning	Hanqiu Li Cai et al.	arXiv	29
2026-10-08	2610.04722	NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis	Ramil Khafizov et al.	arXiv	29
2026-10-08	2610.08760	WorldSonus: Bringing Sound to Worlds	Pengjun Fang et al.	arXiv	29
2026-10-08	2610.10437	Q-Learning with Scalar Adjoint Matching	Yonghoon Dong et al.	arXiv	25
2026-10-08	2610.07591	Recurrent Looped Transformer	Yifan Zhang et al.	arXiv	25
2026-10-08	2610.09484	MIMESIS: Learning User Simulators as Training Environments for Interactive Agents	Hoang Phan et al.	arXiv	23
2026-10-08	2610.09127	CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use	Gennadiy Savrasov et al.	arXiv	23
2026-10-08	2610.07874	On-Policy Distillation with Negative-Policy Rollouts	Jaehui Hwang et al.	arXiv	21
2026-10-08	2609.40360	Semifactual Credit-Augmented Policy Optimization	Junshu Pan et al.	arXiv	20
2026-10-08	2610.06293	VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction	Qiutong Chen et al.	arXiv	19
2026-10-08	2610.00994	VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations	Xianda Du et al.	arXiv	19
2026-10-08	2610.10114	Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position	Xiaoran Liu et al.	arXiv	19
2026-10-08	2610.09684	From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery	Xinglin Wang et al.	arXiv	18
2026-10-08	2610.10497	QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation	Yucheng Mao et al.	arXiv	17
2026-10-08	2610.07862	A self-learning scientific agent for X-ray diffraction	Bin Cao et al.	arXiv	16
2026-10-08	2610.07250	Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation	Wenxuan Wang et al.	arXiv	16
2026-10-08	2610.09832	SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles	Yuyao Ge et al.	arXiv	16
2026-10-08	2610.07659	DLoop: Looped Speculative Decoding	Geonmo Gu et al.	arXiv	15
2026-10-08	2610.05289	Mobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian Splatting	Xiaobiao Du et al.	arXiv	15
2026-10-08	2610.05336	SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision	Junyan Jiang et al.	arXiv	13
2026-10-08	2610.09920	Inverting Multi-Vector Visual Document Indices	Zhuchenyang Liu et al.	arXiv	13
2026-10-08	2610.02396	Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance	Songtao Wei et al.	arXiv	12
2026-10-08	2610.06505	Improving Proactive AI Assistance with Hierarchical Procedural Understanding	Jin-Seop Lee et al.	arXiv	12
2026-10-08	2610.08963	On KL-Regularized Policy Optimization	Yifan Zhang	arXiv	12
2026-10-08	2610.10845	Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute	Sietse Schelpe	arXiv	10
2026-10-08	2610.10460	Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts	Hejian Sang et al.	arXiv	10
2026-10-08	2609.33659	Learning Multimodal Embeddings with Evidence-Aligned Readout	Zirong Chen et al.	arXiv	10
2026-10-08	2610.07226	Minimal Witness Reinforcement Learning	T. Y. Tsui et al.	arXiv	10
2026-10-08	2610.05034	Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads	Jingjie Ning et al.	arXiv	10
2026-10-08	2610.10164	UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy	Yifei Lu et al.	arXiv	9
2026-10-08	2610.10533	EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory	Hongru Cai et al.	arXiv	9
2026-10-08	2610.10047	AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation	Zhifei Yang et al.	arXiv	7
2026-10-08	2610.03036	WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites	Jiangang Han	arXiv	7
2026-10-08	2610.08902	Agent Plasticity: Measuring Self-Improvement Through Experience	Harman Singh et al.	arXiv	6
2026-10-08	2610.10515	RoboJEPA: Scaling Robotic Latent World Models	Artem Zholus et al.	arXiv	6
2026-10-08	2609.38466	PAMI: Part Anchored Motion for Text to Human-Object Interaction Generation	Chuqiao Li et al.	arXiv	5
2026-10-08	2610.03799	StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search	Ghadi Nehme et al.	arXiv	5
2026-10-08	2610.05324	CoDance: Learning Reactive and Compliant Human-Humanoid Interaction from Video	Zhuoqun Chen et al.	arXiv	4
2026-10-08	2609.36995	Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation	Xingtong Ge et al.	arXiv	4
2026-10-08	2610.10388	RoboQuest: Generalist Physical Agents that Search, Inspect and Test	Liu Renhang et al.	arXiv	4
2026-10-08	2609.30541	AutoResearch at Production Scale: Failure Modes and a Multi-Agent Framework	Aparajith Chandran et al.	arXiv	3
2026-10-08	2610.04012	Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models	A. Bochkov	arXiv	3
2026-10-08	2610.09457	DSReg: Provably Recovering Individual World Latents without Reconstruction	Yujia Zheng et al.	arXiv	3
2026-10-08	2610.05003	How corner is a corner case? Percentile control for highway scenario generation	Jiaxi Liu et al.	arXiv	2
2026-10-08	2610.07258	Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents	Venkata M Sangaraju et al.	arXiv	2
2026-10-08	2610.09683	System Switch: When Should a Fast Decision Model Stop and Think?	Gian Luca Bailo	arXiv	2
2026-10-08	2605.09742	TIDES: Implicit Time-Awareness in Selective State Space Models	Taylan Soydan et al.	arXiv	2
2026-10-08	2610.02832	FastOPD: On-Policy Distillation for Lightweight VLA Deployment	Yoojin Oh et al.	arXiv	2
2026-10-08	2610.08884	Task-Sufficient Contraction: Source Selection for Machine Information Interfaces	Joss Armstrong	arXiv	2
2026-10-08	2609.38562	LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation	Byoungwoo Park et al.	arXiv	1
2026-10-08	2609.38680	ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images	Shubhang Bhatnagar et al.	arXiv	1
2026-10-08	2610.09228	Co-Evolving Robot Orchestrators and Policies through Deployment	Xilun Zhang et al.	arXiv	1
2026-10-07	2610.03543	DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation	Jiahao Zhan et al.	arXiv	95
2026-10-07	2610.08448	Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability	Bingxi Hou et al.	arXiv	59
2026-10-07	2610.07767	TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models	Xin Wang et al.	arXiv	55
2026-10-07	2610.05030	EVISKILL: Grounding Skill Evolution in Replayable Evidence	Yan Zhou et al.	arXiv	51
2026-10-07	2610.07043	TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning	Zhen Li et al.	arXiv	45
2026-10-07	2610.07753	From Evidence to Action: How Tool-Using Agents Fail	Hongzhan Lin et al.	arXiv	45
2026-10-07	2609.37334	Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing	Sohyun Lee et al.	arXiv	43
2026-10-07	2610.05966	HuatuoGPT-3: RL-Only Domain Adaptation from Base Models	Junying Chen et al.	arXiv	41
2026-10-07	2610.09455	RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning	Seungjun Moon et al.	arXiv	39
2026-10-07	2610.03607	World Action Learning via Interaction-Centric Spectral Latent Guidance	Zhiming Liu et al.	arXiv	39
2026-10-07	2610.05140	AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents	Dongki Kim et al.	arXiv	39
2026-10-07	2610.05912	MiniCorp: The Last Mile of the AI Agent Firm	Jingying Zeng et al.	arXiv	36
2026-10-07	2610.01892	Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents	Feiyu Gavin Zhu et al.	arXiv	32
2026-10-07	2610.08430	NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale	Songlin Jiang et al.	arXiv	28
2026-10-07	2609.29792	TimeBraid: Unifying Time Series and Language for Understanding and Forecasting	Xinyue Wang et al.	arXiv	27
2026-10-07	2610.08463	UNREAL: Unifying Retrieval and Long-Context with a Single Model	Edan Kinderman et al.	arXiv	25
2026-10-07	2610.01218	AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation	Giulio Zeloni et al.	arXiv	25
2026-10-07	2610.08791	World Models' Last Exam in Physics	Mingju Gao et al.	arXiv	25
2026-10-07	2609.38972	Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment	Yihuai Hong et al.	arXiv	23
2026-10-07	2610.07557	CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?	Hang He et al.	arXiv	21
2026-10-07	2609.32921	Adaptive Latent Capacity for World Models	Idan Achituve et al.	arXiv	21
2026-10-07	2610.00948	GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution	Geyi Yang et al.	arXiv	21
2026-10-07	2610.04596	DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation	Karn Tiwari et al.	arXiv	20
2026-10-07	2609.40127	Learning Functional Subspaces for Neural Network Compression	Massimo Bini et al.	arXiv	18
2026-10-07	2609.34117	SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving	Gunho Park et al.	arXiv	18
2026-10-07	2610.06960	DistScene: Object-to-Scene Distillation for 3D Scene Generation	Kunming Luo et al.	arXiv	18
2026-10-07	2610.07969	EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation	Yikai Qin et al.	arXiv	18
2026-10-07	2610.08773	AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model	Sarim Hashmi et al.	arXiv	16
2026-10-07	2610.04933	DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling	Seongheon Park et al.	arXiv	16
2026-10-07	2610.02858	Harness-Aware Distillation for Small Language Model Agents	Moonseok Choi et al.	arXiv	15
2026-10-07	2610.08790	Building Rome from a Single Image	Jiraphon Yenphraphai et al.	arXiv	15
2026-10-07	2610.08778	Sherpa: Teaching LLMs to Teach Adaptively	Weixian Xu et al.	arXiv	14
2026-10-07	2610.00864	Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models	Jiawei Fan et al.	arXiv	14
2026-10-07	2610.02781	OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation	Xinpeng Wang et al.	arXiv	14
2026-10-07	2610.05842	HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing	Zhuokun Chen et al.	arXiv	14
2026-10-07	2610.07641	Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution	Kyudan Jung et al.	arXiv	14
2026-10-07	2610.07727	HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models	Kyudan Jung et al.	arXiv	14
2026-10-07	2610.07510	Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training	Qiusi Zhan et al.	arXiv	13
2026-10-07	2610.09243	We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents	Kefan Liu et al.	arXiv	12
2026-10-07	2610.08630	Towards In-Parameter Memory Augmentation for Large Language Models	Haoyu Huang et al.	arXiv	12
2026-10-07	2610.07342	Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding	Hoang Phan et al.	arXiv	11
2026-10-07	2610.08048	DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks	Antoine Edy et al.	arXiv	11
2026-10-07	2610.07832	Harness Engineering for Software Engineering via Modular Executable Dev-Primitives	Haibo Jin et al.	arXiv	11
2026-10-07	2609.35378	Multilinguality in Hybrid Attention LLMs	Lucas Bandarkar et al.	arXiv	10
2026-10-07	2610.06844	Learning to Read the Contextual Tokens in Diffusion Transformers	Omer Dahary et al.	arXiv	10
2026-10-07	2610.07588	Personal-Agent Mediated Recommendation with Cross-Platform User History	Yu Xia et al.	arXiv	10
2026-10-07	2610.08761	VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning	Zewei Zhou et al.	arXiv	9
2026-10-07	2610.08779	ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing	Zhenghong Zhou et al.	arXiv	9
2026-10-07	2609.29123	Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning	Yoomee Cho et al.	arXiv	7
2026-10-07	2610.07785	Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents	Gyusik Seo et al.	arXiv	7
2026-10-07	2610.07348	Stepped MoE: Segment-Level Routing with Configurable Inference Complexity	Arnav Kundu et al.	arXiv	5
2026-10-07	2610.04002	Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale	A. Bochkov	arXiv	5
2026-10-07	2610.04703	Learning Discriminative Geometry for Drifting Models	Doudou Zhang et al.	arXiv	5
2026-10-07	2610.07332	Structuring MoE Expert Selection for Agentic Reinforcement Learning	Bolian Li et al.	arXiv	4
2026-10-07	2610.02188	DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation	Zhengming Yu et al.	arXiv	4
2026-10-07	2610.08244	Sensor-Language-Action Models	Yuekai Xu et al.	arXiv	4
2026-10-07	2610.08777	CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching	Shangye Song et al.	arXiv	4
2026-10-07	2610.05967	JLD: Perceptual Distance Through A Jacobian Lens	Shreshth Saini et al.	arXiv	4
2026-10-07	2610.06191	Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions	Chubin Zhang et al.	arXiv	4
2026-10-07	2609.13730	JumpStart Your Policy Learning with Lessons from 160,000 Training Runs	Nabil Omi et al.	arXiv	3
2026-10-07	2610.05166	A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies	Tu Nguyen et al.	arXiv	3
2026-10-07	2610.05954	MEND: RL For Flow Models via Proximal Velocity Matching	Shreshth Saini et al.	arXiv	3
2026-10-07	2610.05949	Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco	Abdelghani Belgaid et al.	arXiv	2
2026-10-07	2610.01921	Cross-Lingual Alignment for Decoder-Only Models using MoE Routers	Lucas Bandarkar et al.	arXiv	2
2026-10-07	2610.06847	S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation	Jeffrey Hu et al.	arXiv	2
2026-10-07	2610.06104	Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks	Di Wu et al.	arXiv	2
2026-10-07	2610.06090	Execution-Aligned Progressive Noise for Consistent Asynchronous Replanning in Generative Robot Policies	Di Wu et al.	arXiv	2
2026-10-07	2609.39822	Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation	Di Wu et al.	arXiv	2
2026-10-07	2609.39870	Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence	Xuhua Chen et al.	arXiv	2
2026-10-07	2610.07384	WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification	Turhan Can Kargin et al.	arXiv	2
2026-10-07	2610.00417	Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution	Joss Armstrong	arXiv	2
2026-10-07	2610.04605	ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution	Yehonatan Elisha et al.	arXiv	2
2026-10-06	2610.05608	Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation	Team Kandinsky et al.	arXiv	167
2026-10-06	2610.04198	ALoDLM: Adaptively Looped Diffusion Language Models	Liancheng Fang et al.	arXiv	74
2026-10-06	2610.05162	Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy	Ruqing Ning et al.	arXiv	57
2026-10-06	2610.06647	LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches	Shaokun Zhang et al.	arXiv	45
2026-10-06	2610.03120	In-Distribution Forcing for Long Video Generation at Test Time	Jeongwoo Shin et al.	arXiv	45
2026-10-06	2609.37267	Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym	Jio Oh et al.	arXiv	36
2026-10-06	2610.04292	LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures	Jiateng Liu et al.	arXiv	34
2026-10-06	2610.05107	SearchJev: A Fast and Calibrated System-1 Model for Search Agents	Congfeng Cao et al.	arXiv	32
2026-10-06	2610.06833	Towards Looped Models Done Right, Part II: Rethinking at Fixed Points	Benhao Huang et al.	arXiv	29
2026-10-06	2610.05719	When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models	Seonghoon Yu et al.	arXiv	27
2026-10-06	2609.39490	OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning	Junming Lin et al.	arXiv	26
2026-10-06	2610.06648	Representation-Space MMD for Diffusion Language Models	Ilya Drobyshevskiy et al.	arXiv	26
2026-10-06	2610.04109	SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting	Mingtian Tan et al.	arXiv	25
2026-10-06	2610.02331	World Editing: Intervening on Executable Worlds at Increasing Depth	Max Ku et al.	arXiv	24
2026-10-06	2609.36099	Data Unlearning via Inverse Distillation	Aleksei Leonov et al.	arXiv	23
2026-10-06	2609.24890	OSWorld-Pro: Process-based Evaluation for Computer Use Agents	Zhilin Wang et al.	arXiv	23
2026-10-06	2610.05076	Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation	Cheng Luo et al.	arXiv	22
2026-10-06	2610.06577	Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation	Artem Tsypin et al.	arXiv	21
2026-10-06	2610.06851	Base Models Can Reason By Taking a Cue From Training Data	Sophie L. Wang et al.	arXiv	21
2026-10-06	2610.05303	ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience	Haodong Lu et al.	arXiv	21
2026-10-06	2610.00923	CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG	Hyojeong Yun et al.	arXiv	20
2026-10-06	2610.05750	Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks	Reza Esfandiarpoor et al.	arXiv	17
2026-10-06	2610.05622	UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents	Dolly Sah et al.	arXiv	17
2026-10-06	2610.04929	RobotUse: Allocating Computation, Context, and Decisions	Junhoo Lee et al.	arXiv	17
2026-10-06	2610.05416	Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training	Shuyuan Tu et al.	arXiv	17
2026-10-06	2609.36684	ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context	Jianshu Zhang et al.	arXiv	16
2026-10-06	2610.06361	Capability-Driven Self-Evolution of Agent Memory	Yaoqi Chen et al.	arXiv	15
2026-10-06	2610.04616	PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training	Mingyu Liu et al.	arXiv	15
2026-10-06	2609.39420	QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code	Alexey Chernysh et al.	arXiv	15
2026-10-06	2609.34227	When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model	Rishabh Sharma et al.	arXiv	14
2026-10-06	2610.02076	LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them	Yinheng Li et al.	arXiv	14
2026-10-06	2610.02320	DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents	A. Said Gurbuz et al.	arXiv	14
2026-10-06	2610.05894	Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering	Sarim Hashmi et al.	arXiv	14
2026-10-06	2610.05870	Certification of Real Images through Calibrated Content Authentication	Sarim Hashmi et al.	arXiv	14
2026-10-06	2609.36691	Video2Skill: From Streaming Experience to Reusable Embodied Skills	Jianshu Zhang et al.	arXiv	13
2026-10-06	2610.05739	HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models	Zhuokun Chen et al.	arXiv	13
2026-10-06	2609.35751	How to Loop MoE: Flatten the Experts, Untie the Attention	Shouren Wang et al.	arXiv	13
2026-10-06	2610.02191	The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models	Shuo Xing et al.	arXiv	12
2026-10-06	2610.06617	RealtimeWAM: One-Step Asynchronous World Action Models	Chengtao Lv et al.	arXiv	12
2026-10-06	2610.04318	Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency	Sixun Dong et al.	arXiv	11
2026-10-06	2610.06666	What Matters for Latent Reasoning with Flow Matching	Yassine Ouali et al.	arXiv	10
2026-10-06	2610.02150	From Knowledge Access to Source Learning: Developing Source-Specific Competence	Lucheng Fu et al.	arXiv	10
2026-10-06	2610.04137	Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction	Som Sagar et al.	arXiv	10
2026-10-06	2610.04128	What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document	Georgios Politis et al.	arXiv	9
2026-10-06	2610.06545	Empirical Variational Autoencoder	Kaede Shiohara	arXiv	8
2026-10-06	2610.05538	LiFT: Loop Flow Transformers	Mohammad Mahdi Derakhshani et al.	arXiv	8
2026-10-06	2610.03872	Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery	Peter Chen et al.	arXiv	8
2026-10-06	2610.04226	PaLoRA: Paced Low-Rank Adaptation for Continual Learning	Yuxuan Li et al.	arXiv	7
2026-10-06	2609.32423	PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins	Yaorui Shi et al.	arXiv	7
2026-10-06	2605.21318	TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization	Lucheng Fu et al.	arXiv	6
2026-10-06	2610.04631	The Numerical Linear Algebra of Large Language Models	Abdelkader Baggag et al.	arXiv	5
2026-10-06	2610.05879	Learning to Learn a Language	Lennart Carstens-Behrens et al.	arXiv	5
2026-10-06	2610.04047	Periscope: Extending Frozen Language Models Beyond Their Context Window	Mohamed Eltahir et al.	arXiv	5
2026-10-06	2610.05033	Code2Games: Enabling Coding Agents for Gaming World Generation	Wei Wu et al.	arXiv	5
2026-10-06	2610.02586	Labels Override Definitions in Jev-Style Typed Decision Models	Seyedarmin Azizi et al.	arXiv	4
2026-10-06	2610.05898	Collaborative Personalized Preference Alignment for LLMs under Data Deficiency	Liyan Yang et al.	arXiv	4
2026-10-06	2610.02459	OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies	Zhaoyang Chu et al.	arXiv	4
2026-10-06	2610.04426	UnAct: Gradient-Free Unlearning via Targeted Activation Intervention	Saeed Abdul Muizz et al.	arXiv	3
2026-10-06	2610.06804	Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution	Erfan Baghaei Potraghloo et al.	arXiv	3
2026-10-06	2610.03252	COSMI: COmpositional Synthesis of Multi-object Interactions	Daniel Eskandar et al.	arXiv	3
2026-10-06	2610.03978	Learning Latent Protein Languages for Autoregressive Generation	Mahdi Pourmirzaei et al.	arXiv	3
2026-10-06	2609.35652	MM-ABC: Towards Generalist Mobile Manipulation via Seeing, Coordinating and Imagining	Qiwei Liang et al.	arXiv	3
2026-10-06	2610.02480	MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations	Yuyang Cheng et al.	arXiv	3
2026-10-06	2609.37496	GeoSET: Generalist Foundation Model for SAR-to-EO Image Translation	Jeonghyeok Do et al.	arXiv	3
2026-10-06	2610.06425	SoK: Semantic Decision Engines in Network Control Loops	Delong Li et al.	arXiv	3
2026-10-06	2609.23136	Intent Interpretation at RIC Timescales: Jev Decision Models versus Large Language Models in 6G Open RAN	Delong Li et al.	arXiv	3
2026-10-06	2609.31662	Learning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment	Guray Ozgur et al.	arXiv	3
2026-10-06	2610.02999	OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination	Huiqiang Rong et al.	arXiv	3
2026-10-06	2610.02417	The AI Theorist reveals excitonic structure in α-RuCl_3	Hongjian Zhou et al.	arXiv	2
2026-10-06	2610.04749	Agentic discovery of blood biomarker from distilled private health records	Seffi Cohen et al.	arXiv	2
2026-10-06	2610.06679	Closing the Context Gap: Activation Alignment for Tabular In-Context Learning	Yoel Zeldes	arXiv	2
2026-10-06	2605.16817	Adaptive Fused Prior Transfer for Controllable Generative Image Compression	Yifei Pei et al.	arXiv	2
2026-10-06	2610.01789	iADD: Improving Alignment and Diversity in Diffusion Policy Optimization	Ashok Prasad Neupane et al.	arXiv	2
2026-10-06	2610.05790	FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Models	Md Aminur Hossain et al.	arXiv	2
2026-10-06	2610.06693	Adapting prior-data fitted networks for tabular anomaly detection	Maximilian Bershtman et al.	arXiv	2
2026-10-06	2609.32510	GeoCR: Learning a Generalist Cloud Removal Prior from Heterogeneous Observations	Jeonghyeok Do et al.	arXiv	2
2026-10-06	2610.04211	CurveCodec 2: Skeleton-agnostic animation compression with a learned entropy model	Mingyi Shi et al.	arXiv	2
2026-10-06	2610.06184	Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models	Zaibin Zhang et al.	arXiv	2
2026-10-06	2610.06850	InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation	Yucheng Zhang et al.	arXiv	2
2026-10-06	2610.03123	Foresight: planning future perception in streaming VLMs without retraining	Ashok Prasad Neupane et al.	arXiv	1
2026-10-06	2610.03617	DEPICT: Scoring Text-to-Image Alignment by Answer Agreement	Vasco Ramos et al.	arXiv	1
2026-10-05	2610.02508	World Action Modeling with Progressive Visual Planning	Fei Zhang et al.	arXiv	87
2026-10-05	2610.03391	Native Action-Prior Learning from Videos for World Action Models	Zhaochong An et al.	arXiv	66
2026-10-05	2610.02840	PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation	Chunghyun Park et al.	arXiv	62
2026-10-05	2609.38078	MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation	Bingxuan Li et al.	arXiv	55
2026-10-05	2609.38839	FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation	Bo Yin et al.	arXiv	55
2026-10-05	2610.02381	Latent-MOPD: Latent Multi-Teacher On-Policy Distillation	Zhengyu Fang et al.	arXiv	43
2026-10-05	2609.38879	Does Learning Protein Folding Generalize to Broader Reasoning?	Yong Liu et al.	arXiv	43
2026-10-05	2610.02826	Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite	Zongxia Li et al.	arXiv	42
2026-10-05	2610.01780	RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations	Arman Behnam et al.	arXiv	38
2026-10-05	2610.03665	Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models	Seo Hyun Kim et al.	arXiv	37
2026-10-05	2609.34715	PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs	Zhentao Tan et al.	arXiv	36
2026-10-05	2610.02304	SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation	Ruiqi Zhang et al.	arXiv	35
2026-10-05	2610.00531	Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers	Yerim Oh et al.	arXiv	32
2026-10-05	2609.36659	On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training	Shufan Shen et al.	arXiv	30
2026-10-05	2609.39071	LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models	Yida Cai et al.	arXiv	29
2026-10-05	2610.00972	VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks	Caiqi Zhang et al.	arXiv	27
2026-10-05	2610.03195	Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It	Jonghyun Song et al.	arXiv	26
2026-10-05	2610.03632	World Embedding Benchmark	Yiqi Liu et al.	arXiv	26
2026-10-05	2610.03574	HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents	Alham Fikri Aji et al.	arXiv	25
2026-10-05	2610.03367	Multilingual GSM-Symbolic: What determines capability transfer across languages?	Kenneth Enevoldsen et al.	arXiv	24
2026-10-05	2610.03695	Language Models that Play Chess and Explain Their Moves	Adithya Bhaskar et al.	arXiv	23
2026-10-05	2610.02521	Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory	Ying Yang et al.	arXiv	23
2026-10-05	2610.03715	4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes	Ruihong Shen et al.	arXiv	21
2026-10-05	2609.36887	WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents	Bo Mao et al.	arXiv	20
2026-10-05	2609.39820	Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models	Mingyue Cui et al.	arXiv	19
2026-10-05	2609.36529	Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling	Oliver Sieberling et al.	arXiv	19
2026-10-05	2610.02298	EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling	Ruihan Yu et al.	arXiv	19
2026-10-05	2610.01153	Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts	Di He et al.	arXiv	18
2026-10-05	2610.01257	Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems	Yiqiao Jin et al.	arXiv	18
2026-10-05	2610.02824	MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning	Yuxuan Fan et al.	arXiv	17
2026-10-05	2610.03509	Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability	Samuel Lewis-Lim et al.	arXiv	15
2026-10-05	2610.03664	ProAR: Learning Prospective Reasoning with Autoregressive Video Models	Linghui Shen et al.	arXiv	15
2026-10-05	2610.03675	FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution	Hui Chen et al.	arXiv	14
2026-10-05	2609.38123	HelixWorld: A Real-time Interactive Audio-Visual World Model	Lei Ke et al.	arXiv	13
2026-10-05	2609.32777	DEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS	Ambuj Mehrish et al.	arXiv	13
2026-10-05	2609.30467	Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification	Heyuan Huang et al.	arXiv	12
2026-10-05	2609.26425	QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models	Jiaqi Zhao et al.	arXiv	11
2026-10-05	2610.02179	From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation	Siqi Zhu et al.	arXiv	11
2026-10-05	2609.39050	Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems	Deema Alnuhait et al.	arXiv	11
2026-10-05	2610.02388	Octrees as an Explicit 3D Language	Ran Dan et al.	arXiv	11
2026-10-05	2609.28339	Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control	Zanyi Wang et al.	arXiv	10
2026-10-05	2608.26762	Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers	Markus Frohmann et al.	arXiv	10
2026-10-05	2610.02710	Self-Supervised Scaling of Terminal Environments for Scientific Domains	Zhongzhi Li et al.	arXiv	9
2026-10-05	2609.37925	Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation	Chenjian Gao et al.	arXiv	8
2026-10-05	2610.03240	Collective Bias Mitigation via Model Routing and Collaboration	Mingzhe Du et al.	arXiv	8
2026-10-05	2609.34826	WM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning	Yuheng Zha et al.	arXiv	7
2026-10-05	2610.03710	EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras	Kush Hari et al.	arXiv	7
2026-10-05	2609.38096	Tail-Influence Sampling for CVaR Policy Evaluation	Pauline Bourigault et al.	arXiv	7
2026-10-05	2609.40153	Dream4ACT: A Shared Visual Action Interface for Multi-Embodiment Video-Action Modeling	Xiangyu Zhu et al.	arXiv	7
2026-10-05	2610.02126	Local Support Learning	Assaf Ben-Kish et al.	arXiv	7
2026-10-05	2609.39963	Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production	Chongjun Zhong et al.	arXiv	7
2026-10-05	2609.26590	GTR: Gated Token Recurrence for Efficient Dense Prediction	Zhe Feng et al.	arXiv	7
2026-10-05	2610.04116	CUAWright: A Minimal Unified Interface for Digital Agents	Yadong Lu et al.	arXiv	6
2026-10-05	2609.32182	KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding	Zihan Chen et al.	arXiv	6
2026-10-05	2609.33804	MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception	Yuhao Li et al.	arXiv	6
2026-10-05	2610.02788	Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation	Xincheng He et al.	arXiv	6
2026-10-05	2609.32046	Receiver-Conditioned Latent Communication gives 94% CacheBack	Maximillian Rossi et al.	arXiv	5
2026-10-05	2609.34895	LVMT: Video Mask Transformer for Long-term Video Segmentation	Narges Norouzi et al.	arXiv	5
2026-10-05	2609.39394	Can Computation from Earlier Problems Help LLMs Solve New Ones?	Jipei He et al.	arXiv	4
2026-10-05	2610.00722	JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts	Zheyuan Zhang et al.	arXiv	3
2026-10-05	2610.02772	Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing	Ding Wu et al.	arXiv	3
2026-10-05	2609.32759	The Extender: A Log-Structured Transformer	Jakob Eriksson	arXiv	3
2026-10-05	2610.02486	From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders	Pritam Deka	arXiv	3
2026-10-05	2609.33463	Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features	Cunchun Li et al.	arXiv	2
2026-10-05	2609.38325	Strike a Chord! Modal Kinetic Typography	Maham Tanveer et al.	arXiv	1
2026-10-02	2610.01509	Sharpening Tax in Post-Training	Changdae Oh et al.	arXiv	89
2026-10-02	2610.01762	OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction	Xiangyu Zeng et al.	arXiv	77
2026-10-02	2610.02193	Hierarchical Continuous Diffusion Language Models	Hui Ren et al.	arXiv	74
2026-10-02	2610.02162	World Observer: Joint Actor-Observer Generation for Persistent World Modeling	Hyunwook Choi et al.	arXiv	63
2026-10-02	2610.01415	Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States	Yu Luo et al.	arXiv	63
2026-10-02	2610.00906	ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization	Sungho Park et al.	arXiv	59
2026-10-02	2609.32993	X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization	Sitao Cheng et al.	arXiv	58
2026-10-02	2609.38923	GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis	Qisheng Su et al.	arXiv	58
2026-10-02	2609.35690	Agent Priors-guided Policy Learning	Puming Jiang et al.	arXiv	54
2026-10-02	2609.39378	EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos	Shulin Tian et al.	arXiv	47
2026-10-02	2610.02205	PROWBench: Do Video Models Render What the Program Specifies?	Zheng-Hui Huang et al.	arXiv	46
2026-10-02	2609.37533	E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models	Arseny Ivanov et al.	arXiv	44
2026-10-02	2609.38024	Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation	Jaewon Chu et al.	arXiv	40
2026-10-02	2609.35259	On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics	Julianna Piskorz et al.	arXiv	39
2026-10-02	2609.32019	Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding	Valeriy Vyaltsev et al.	arXiv	38
2026-10-02	2610.01215	AutoGUIWorld: Image Generators as Visual World Models for GUI Agent	Cheng Yang et al.	arXiv	38
2026-10-02	2610.00559	PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop	Xinge Peng et al.	arXiv	34
2026-10-02	2610.00574	Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL	Tong Zheng et al.	arXiv	33
2026-10-02	2610.02196	InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation	Zhuo Lin et al.	arXiv	31
2026-10-02	2609.39375	Beyond the Current Scene: Event-Referential Grasping with Active View Selection	Hyunjoon Lee et al.	arXiv	30
2026-10-02	2606.10953	Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans	Fedor Rodionov et al.	arXiv	29
2026-10-02	2609.39027	A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review	Chenguang Wang et al.	arXiv	29
2026-10-02	2609.36585	Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It	Zehao Jin et al.	arXiv	28
2026-10-02	2610.01939	Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens	Ruiyang Si et al.	arXiv	26
2026-10-02	2609.32259	Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs	Vincent-Daniel Yun et al.	arXiv	26
2026-10-02	2610.01016	Scaling and Distilling Text Embeddings for Better Diffusibility	Zekai Zhang et al.	arXiv	26
2026-10-02	2610.01092	Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation	Patrick Amadeus Irawan et al.	arXiv	24
2026-10-02	2610.00812	Video Generation Models: A Survey of Post-Training and Alignment	Chaoyu Li et al.	arXiv	24
2026-10-02	2609.40097	AutoDataBench: A Data-centric Testbed for Accelerating Auto Research	Ruifeng Yuan et al.	arXiv	24
2026-10-02	2610.02185	Decoding Looped Transformers Better for (Almost) Free	Weihao Liu et al.	arXiv	23
2026-10-02	2609.36820	CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning	Wenbin Hu et al.	arXiv	23
2026-10-02	2609.40362	Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces	Hongyuan Tao et al.	arXiv	22
2026-10-02	2609.37200	Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL	Songlin Yang et al.	arXiv	22
2026-10-02	2610.02122	Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows	Gabriel Tomitsuka et al.	arXiv	21
2026-10-02	2610.02160	4Director: Controlling Video World Models with Rigid 3D Geometry	Wei Cao et al.	arXiv	20
2026-10-02	2610.02181	OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning	Haibo Wang et al.	arXiv	20
2026-10-02	2610.00964	RPTune: Learned Context Curation for LLM Catalog Search	Chuxuan Hu et al.	arXiv	20
2026-10-02	2609.38886	Benchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation	Yansong Shi et al.	arXiv	19
2026-10-02	2610.02201	SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation	Tianjiao Yu et al.	arXiv	18
2026-10-02	2609.38987	Smaller Models, Better Rejects: Preference Distillation Scaling	Rui Cai et al.	arXiv	17
2026-10-02	2610.02117	Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes	Sophia Sirko-Galouchenko et al.	arXiv	16
2026-10-02	2610.02148	Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation	Mohammed Irfan Kurpath et al.	arXiv	14
2026-10-02	2609.39687	Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation	Xincheng Wei et al.	arXiv	14
2026-10-02	2609.32520	When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents	Yanjie Zhang et al.	arXiv	14
2026-10-02	2609.36388	Persona Dosing: Calibrated Activation Steering for Graded Trait Control	Zehao Jin et al.	arXiv	11
2026-10-02	2609.32810	OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories	Anqi Li et al.	arXiv	11
2026-10-02	2610.02202	ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research	Sohyeon Kim et al.	arXiv	11
2026-10-02	2610.01108	AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines	Sumin Lee et al.	arXiv	11
2026-10-02	2610.00314	Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts	Jingjie Ning et al.	arXiv	11
2026-10-02	2609.33403	DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration	Yupeng Xie et al.	arXiv	10
2026-10-02	2609.40222	LOCI: Spatial Linear Memory for Streaming World Models	Ji Xia et al.	arXiv	9
2026-10-02	2609.37362	Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing	Guannan Lai et al.	arXiv	9
2026-10-02	2609.34210	RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers	Haitong Ma et al.	arXiv	8
2026-10-02	2610.00348	Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation	Minoo Kim et al.	arXiv	8
2026-10-02	2610.02206	KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards	Pengfei Li et al.	arXiv	8
2026-10-02	2610.00825	Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing	Rui Liu et al.	arXiv	8
2026-10-02	2610.00686	SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation	Mikhail Dereviannykh et al.	arXiv	7
2026-10-02	2610.01428	Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs	Nagham Omar et al.	arXiv	7
2026-10-02	2610.01499	VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation	Yu Huang et al.	arXiv	7
2026-10-02	2609.38104	Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling	Panagiotis Theodoropoulos et al.	arXiv	7
2026-10-02	2609.32536	Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents	Yanjie Zhang et al.	arXiv	7
2026-10-02	2610.00483	PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion	Lehan Yang et al.	arXiv	7
2026-10-02	2610.01942	Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models	Efstathios Karypidis et al.	arXiv	6
2026-10-02	2610.00544	Memorizon: Training World Models Beyond Their Context Window	Tingting Liao et al.	arXiv	6
2026-10-02	2609.38593	Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions	Bo Ni et al.	arXiv	6
2026-10-02	2609.38585	FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing	Wang Wei et al.	arXiv	6
2026-10-02	2609.34677	Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models	Beomsu Kim et al.	arXiv	6
2026-10-02	2610.01026	It Takes Workflows to Evolve Better Workflows	Xuehang Guo et al.	arXiv	6
2026-10-02	2610.01017	Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization	Xuehang Guo et al.	arXiv	5
2026-10-02	2610.00737	Personalized Image Generation with Reasoning and Reflection	Bo Ni et al.	arXiv	5
2026-10-02	2610.00313	Rules to Tools: Executable Checks for LLM Agents in Scientific Computing	Jingjie Ning et al.	arXiv	5
2026-10-02	2609.36435	MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization	Jingxuan Wu et al.	arXiv	4
2026-10-02	2610.00437	JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces	Haoyang Su et al.	arXiv	4
2026-10-02	2610.01595	Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs	Youngwoo Shin et al.	arXiv	4
2026-10-02	2609.37568	Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models	Yu Zhang et al.	arXiv	4
2026-10-02	2609.36956	Controlled Decoding Attacks on Black-Box LLMs	Jesson Wang et al.	arXiv	4
2026-10-02	2609.34381	Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy	Abhinav Sharma et al.	arXiv	4
2026-10-02	2609.22753	Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration	Delong Li et al.	arXiv	3
2026-10-02	2609.37690	Honeycomb: Constant-Size Scene Memory Representation for Video World Models	Jack Wei Lun Shi et al.	arXiv	3
2026-10-02	2609.36138	When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs	Jiayi Li et al.	arXiv	3
2026-10-02	2609.34621	Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?	Jiangshan Wang et al.	arXiv	3
2026-10-02	2610.02142	Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models	Juan S. Santillana	arXiv	2
2026-10-02	2609.36602	OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport	Guillaume Besset et al.	arXiv	2
2026-10-02	2610.00360	DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation	Haoyu Wang et al.	arXiv	2
2026-10-01	2609.36484	The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation	Hao Li et al.	arXiv	160
2026-10-01	2609.39102	False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents	Meijia Chen et al.	arXiv	157
2026-10-01	2609.38721	UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement	Fang Wu et al.	arXiv	141
2026-10-01	2609.39982	Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents	Minki Kang et al.	arXiv	95
2026-10-01	2609.40340	EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery	Young-Jun Lee et al.	arXiv	93
2026-10-01	2609.38288	AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks	Hongjin Qian et al.	arXiv	92
2026-10-01	2609.38143	Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI	Cheng Qian et al.	arXiv	55
2026-10-01	2609.38177	Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering	Jaewoo Jung et al.	arXiv	50
2026-10-01	2609.39045	RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement	Wenyi Wu et al.	arXiv	48
2026-10-01	2609.38426	LoopVL: Recurrent Visual Intelligence	Zhe Qian et al.	arXiv	47
2026-10-01	2609.38827	More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models	Tianxiang Gao et al.	arXiv	46
2026-10-01	2609.40325	WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents	Ziyan Jiang et al.	arXiv	46
2026-10-01	2609.38334	EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making	Yuhan Guo et al.	arXiv	36
2026-10-01	2609.38597	PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation	Cong Wei et al.	arXiv	33
2026-10-01	2609.32264	LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models	Pavel Tikhonov et al.	arXiv	33
2026-10-01	2609.40111	Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training	Kunlun Zhu et al.	arXiv	33
2026-10-01	2609.38445	AIM: Agentic Idea Management for Automated Research	Hyeong Kyu Choi et al.	arXiv	32
2026-10-01	2609.34563	Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence	Xi Xiao et al.	arXiv	28
2026-10-01	2609.39841	DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes	Merav Keidar et al.	arXiv	28
2026-10-01	2609.39903	OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software	Dingyuan Dai et al.	arXiv	27
2026-10-01	2609.32720	BiasReducer: Adaptive Bias Mitigation for Reward Models	Shuang Liu et al.	arXiv	25
2026-10-01	2609.33355	Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models	Injin Kong et al.	arXiv	25
2026-10-01	2609.39222	DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence	Xu Huang et al.	arXiv	25
2026-10-01	2609.38653	TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion	Merkourios Simos et al.	arXiv	23
2026-10-01	2609.39578	Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?	Minghan Wang et al.	arXiv	23
2026-10-01	2609.38660	Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation	Haibo Jin et al.	arXiv	22
2026-10-01	2609.38537	Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies	Galbot Team et al.	arXiv	21
2026-10-01	2609.37863	It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them	Nagham Omar et al.	arXiv	20
2026-10-01	2609.34599	The Low-Rank Structure of VLA Reinforcement Learning	Minjae Oh et al.	arXiv	19
2026-10-01	2609.38349	MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution	Prithwish Jana et al.	arXiv	18
2026-10-01	2609.40316	Scaling Laws for Looped Mixture of Experts	Yanbei Chen et al.	arXiv	18
2026-10-01	2609.40285	PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents	Yinghui He et al.	arXiv	18
2026-10-01	2609.40358	Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model	Liming Lu et al.	arXiv	16
2026-10-01	2609.39564	A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?	Seonho Lee et al.	arXiv	16
2026-10-01	2609.32600	CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering	Prince Zizhuang Wang et al.	arXiv	15
2026-10-01	2609.40048	CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding	Yiduo Jia et al.	arXiv	14
2026-10-01	2609.33711	DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation	Ao Yu et al.	arXiv	14
2026-10-01	2609.38121	WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms	Jiale Chen et al.	arXiv	14
2026-10-01	2609.38658	Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning	Jian Chen et al.	arXiv	13
2026-10-01	2609.38541	ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing	Donghao Zhou et al.	arXiv	13
2026-10-01	2609.39661	The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends	Zhentao Tan et al.	arXiv	12
2026-10-01	2609.38142	AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation	Rishabh Agrawal et al.	arXiv	12
2026-10-01	2609.35646	Rubric Rewards from Item Response Theory	Milad Yazdani et al.	arXiv	11
2026-10-01	2609.37539	SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation	Renxi Wang et al.	arXiv	11
2026-10-01	2609.39685	RoboCoach: World Models as Active Coaches for Compositional Robot Skills	Jiajun Liu et al.	arXiv	11
2026-10-01	2609.34736	SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing	Vasilis Perifanis et al.	arXiv	10
2026-10-01	2609.39827	Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior	Atsuki Yamaguchi et al.	arXiv	9
2026-10-01	2609.40333	I Have a Stream: Making Self-Supervised Learning Work on Continuous Video	Ivan Martinović et al.	arXiv	9
2026-10-01	2609.38807	PatchHolmes: Agentic Patch Retrieval via Listwise Selection	Guanqun Yang et al.	arXiv	8
2026-10-01	2609.37915	Overcoming Scaling Limits in On-Policy Self-Distillation for LLM Reasoning	Md. Ismail Hossain et al.	arXiv	7
2026-10-01	2609.37569	Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering	Yazhen Xie et al.	arXiv	7
2026-10-01	2609.39788	Safety of Latent Communication in Multi-Agent Systems	Muhammad Huzaifa et al.	arXiv	6
2026-10-01	2609.38822	SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale	Guanqun Yang et al.	arXiv	6
2026-10-01	2609.38792	Training LLM Judges from Language Feedback via Position-Selective Self-Distillation	Ilgee Hong et al.	arXiv	5
2026-10-01	2609.39154	DAGent: Evaluate-then-Grow Planning for Deep Research Agents	Hanwen Liu et al.	arXiv	5
2026-10-01	2609.38854	Mitigating the Length-Scaling Tax with Online Distillation	Xu Wan et al.	arXiv	4
2026-10-01	2609.40295	How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text	Jenna Russell et al.	arXiv	4
2026-10-01	2609.18587	Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces	Naveen Vakada et al.	arXiv	4
2026-10-01	2609.40241	Decision-Oriented Recommendation Reranking: An Empirical Study of Jev	Hanjia Lyu et al.	arXiv	4
2026-10-01	2609.40137	Game-Guided Skill Discovery through Self-Play for Playable Agent Control	Seungeun Rho et al.	arXiv	4
2026-10-01	2609.29142	Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD	Yibo Zhao et al.	arXiv	4
2026-10-01	2609.34970	See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs	Weiqiao Que et al.	arXiv	4
2026-10-01	2609.38814	Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive Transformers	Yilun Liu et al.	arXiv	3
2026-10-01	2609.35928	Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems	Xavier Del Giudice et al.	arXiv	3
2026-10-01	2609.34276	NavHarness: Towards Lifelong Embodied Navigation	Xunyi Zhao et al.	arXiv	3
2026-10-01	2609.40359	Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text	Dulhan Jayalath et al.	arXiv	3
2026-10-01	2609.24555	The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence	Muhan Zhang	arXiv	3
2026-10-01	2609.36333	ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning	Ke Fang et al.	arXiv	3
2026-10-01	2609.36931	Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation	Mario Sanz-Guerrero et al.	arXiv	3
2026-10-01	2609.39358	Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost	Sietse Schelpe	arXiv	3
2026-10-01	2609.30840	Aligning One-Step Generative Models with Reward-Weighted Transport Distillation	Austin Wang et al.	arXiv	2
2026-10-01	2609.34274	BIABench: Evaluating AI agents on real-world bioimage analysis tasks	Zixuan Pan et al.	arXiv	2
2026-10-01	2609.40195	MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories	Guangzhi Xiong et al.	arXiv	2
2026-10-01	2609.38717	Soft Spatial Reasoning	Rafi Ibn Sultan et al.	arXiv	2
2026-10-01	2609.39938	LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception	Juyi Lin et al.	arXiv	2
2026-10-01	2609.39166	Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds	Mingjian Gao et al.	arXiv	2
2026-10-01	2609.37879	Retrieval Capacity of Self-Attention Under Competition	Timur Mudarisov et al.	arXiv	2
2026-10-01	2609.37824	The Geometry of Inference in Transformer Residual Streams	Timur Mudarisov et al.	arXiv	2
2026-10-01	2609.34162	SlideDP: Scaling Host-Resident LLM Fine-Tuning Across Multiple GPUs	Ruijia Yang et al.	arXiv	2
2026-10-01	2609.36308	CheatBench: Measuring Reward Gaming in AI Agents	Long Phan et al.	arXiv	2
2026-10-01	2609.40230	EviRover: Reinforcing Agentic Perception Beyond a Glance	Kaixuan Fan et al.	arXiv	2
2026-10-01	2609.35922	Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change	Bhavik Mangla	arXiv	2
2026-10-01	2609.39344	Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings	Shantanu Vispute et al.	arXiv	1
2026-10-01	2609.38716	SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models	Rafi Ibn Sultan et al.	arXiv	1
2026-10-01	2609.37501	Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance	Dipankar Sarkar	arXiv	1
2026-10-01	2605.22493	Understanding Multimodality in Generative Behavioral Cloning	Lorenzo Mazza et al.	arXiv	1