2026-08 papers

2026-11 2026-10 2026-09 2026-08 2026-07 2026-06 2026-05 dispatches about

2026-08 · 645 records

date	id	title	authors	venue	↑
2026-08-31	2608.27550	Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models	Senqiao Yang et al.	arXiv	70
2026-08-31	2608.28122	Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities	Tianfu Wang et al.	arXiv	64
2026-08-31	2608.27549	Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning	Hanyang Wang et al.	arXiv	47
2026-08-31	2608.24804	StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments	Esakkivel Esakkiraja et al.	arXiv	40
2026-08-31	2608.26582	J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data	Gyouk Chu et al.	arXiv	40
2026-08-31	2608.18524	DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents	Hangrui Xu et al.	arXiv	38
2026-08-31	2608.27370	Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090	Kairong Luo et al.	arXiv	37
2026-08-31	2608.27763	Fast Weight Attention for Continual Learning	Yifan Zhang et al.	arXiv	31
2026-08-31	2608.28476	ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL	Zhuoshi Pan et al.	arXiv	31
2026-08-31	2608.23478	Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models	Sangoh Lee et al.	arXiv	30
2026-08-31	2608.27529	Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction	Jiarong Han et al.	arXiv	30
2026-08-31	2608.28460	LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation	Yixuan Ding et al.	arXiv	27
2026-08-31	2608.28281	LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering	Yi Wang et al.	arXiv	23
2026-08-31	2608.28478	Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge	Zhuoshi Pan et al.	arXiv	19
2026-08-31	2608.28444	Sliding-window beats linear attention	Alexia Jolicoeur-Martineau et al.	arXiv	18
2026-08-31	2608.28192	Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding	Hanoona Rasheed et al.	arXiv	17
2026-08-31	2608.26794	Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion	Bowen Xue et al.	arXiv	15
2026-08-31	2608.25417	Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents	Shudong Liu et al.	arXiv	15
2026-08-31	2608.24777	StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing	Zhijie Zheng et al.	arXiv	14
2026-08-31	2608.28549	Video Generative Models as Geometry Learner	Haosen Yang et al.	arXiv	14
2026-08-31	2608.24115	PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control	Suhwan Choi et al.	arXiv	13
2026-08-31	2608.28363	EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses	Tanmay Sah et al.	arXiv	9
2026-08-31	2608.27906	Rubric-to-Code Credit Assignment for Reinforcement Learning	Rui Jin et al.	arXiv	8
2026-08-31	2608.23149	Language Chain in Alignment: Cross-lingual Ranking Preference Optimization	Seungyoon Lee et al.	arXiv	7
2026-08-31	2608.25697	LMSM: LLM Security Framework Inspired by Linux Security Modules	XiuYu Zhang et al.	arXiv	6
2026-08-31	2608.21721	Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention	Xiaoying Song et al.	arXiv	5
2026-08-31	2608.28458	Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents	Nan Li	arXiv	5
2026-08-31	2608.20965	Training, learning and inference: unified dynamics of neural systems	Mian Wang	arXiv	4
2026-08-31	2608.26737	Generative Semantic Scene Completion	Shi Chen et al.	arXiv	3
2026-08-31	2608.26175	Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors	Mantas Lukauskas	arXiv	3
2026-08-31	2608.25375	GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models	Yiqun Sun et al.	arXiv	1
2026-08-28	2608.27448	TTPO: Test-Time Policy Optimization	Aozhe Wang et al.	arXiv	83
2026-08-28	2608.27260	What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents	Xingshan Zeng et al.	arXiv	73
2026-08-28	2608.27456	UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City	Tianjie Ju et al.	arXiv	54
2026-08-28	2608.26872	Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher	Shiyi Zhang et al.	arXiv	41
2026-08-28	2608.27454	WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution	Liyan Tang et al.	arXiv	37
2026-08-28	2608.26530	PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents	Yang Xiao et al.	arXiv	36
2026-08-28	2608.27345	PAWBench: How Far Are We from Probabilistically Aligned World Modeling?	Yuandong Pu et al.	arXiv	36
2026-08-28	2608.25518	Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models	Pengfei Zhou et al.	arXiv	35
2026-08-28	2608.26200	GameWAM: A World Action Model for Video Games	Yuncheng Guo et al.	arXiv	35
2026-08-28	2608.15763	Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report	TaoLive AIGC LLM Team et al.	arXiv	26
2026-08-28	2608.26103	Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization	Jiaming Zhou et al.	arXiv	25
2026-08-28	2608.27351	Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO	Yunpeng Ba et al.	arXiv	20
2026-08-28	2608.26238	Procedura: Agentic 3D Modeling with Procedural Control	Youtian Lin et al.	arXiv	16
2026-08-28	2608.27455	CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes	Yufan Wu et al.	arXiv	12
2026-08-28	2608.23943	Luce: Relightable Gaussians for 3D Asset Generation	Mayank Singh et al.	arXiv	11
2026-08-28	2608.27168	Magpie: Real-Time World Renderer for Interactive Games	Xiaoyu Zhan et al.	arXiv	11
2026-08-28	2608.23172	CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension	Abhilash Nandy et al.	arXiv	9
2026-08-28	2608.26809	Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning	Chenyang Wu et al.	arXiv	6
2026-08-28	2608.25500	CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval	Zhiyuan Li et al.	arXiv	6
2026-08-28	2608.25798	TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback	Jianbo Zhou et al.	arXiv	5
2026-08-28	2608.27123	EditaLive! Unified Character Video Editing for Live Streaming	Zhiyuan Li et al.	arXiv	5
2026-08-28	2608.19269	What Does an Evaluation License? A Commit-Bound Census of Claim Replay in Inspect Evals	Xi Qin et al.	arXiv	4
2026-08-28	2608.26993	Aphanta: Diagnosing Task-Aligned Image-Edited Intermediates for Multimodal Reasoning	Hengyuan Xu et al.	arXiv	3
2026-08-27	2608.24979	FrontierChallenge: Evaluating Scientific Workflow Completion	Liangcai Su et al.	arXiv	152
2026-08-27	2608.26005	VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction	Zhifei Xie et al.	arXiv	133
2026-08-27	2608.26105	VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning	Junxiang Xu et al.	arXiv	76
2026-08-27	2608.19583	VGI-Bench: Probing Visual Intelligence in Video Generation Models	Xuan He et al.	arXiv	57
2026-08-27	2608.25927	Code World Model: Coding Agent as World Brain	Yiwen Chen et al.	arXiv	41
2026-08-27	2608.24479	WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation	Zihao Wu et al.	arXiv	32
2026-08-27	2608.24987	D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation	Zechen Sun et al.	arXiv	28
2026-08-27	2608.23318	Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning	Zixuan Wang et al.	arXiv	23
2026-08-27	2608.23256	Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data	Yinhao Tang et al.	arXiv	22
2026-08-27	2608.19098	Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation	Huan-ang Gao et al.	arXiv	21
2026-08-27	2608.26067	StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models	Zhe Liu et al.	arXiv	20
2026-08-27	2608.25512	A Programming Paradigm for Spatiotemporal Composability	Yifan Shi et al.	arXiv	19
2026-08-27	2608.25529	Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios	Hongbo Liu et al.	arXiv	17
2026-08-27	2608.24358	The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents	Roy Ganz et al.	arXiv	16
2026-08-27	2608.25580	V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning	Shulin Tian et al.	arXiv	16
2026-08-27	2608.23564	SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?	Deyao Hong et al.	arXiv	14
2026-08-27	2608.24138	Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation	Tianyi Xiong et al.	arXiv	13
2026-08-27	2608.24099	Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments	Guo Gan et al.	arXiv	13
2026-08-27	2608.15062	Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation	Amr Hegazy et al.	arXiv	11
2026-08-27	2608.25864	MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization	Zaibin Zhang et al.	arXiv	9
2026-08-27	2608.21832	GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding	Md Abrar Jahin et al.	arXiv	8
2026-08-27	2608.23383	Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds	Nan Duan et al.	arXiv	8
2026-08-27	2608.25832	Skill Issue: Are Skills Language-Invariant in LLMs?	Bobby Cheng et al.	arXiv	6
2026-08-27	2608.24909	Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans	Wentao Jiang et al.	arXiv	6
2026-08-27	2608.19556	Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models	Yuanhao Ban et al.	arXiv	5
2026-08-27	2608.26070	Prefix Sliding for efficient test-time scaling	Niklas Muennighoff et al.	arXiv	4
2026-08-27	2608.25204	LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale	Francesco Mantegna et al.	arXiv	4
2026-08-27	2608.21140	A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans	Simon Vincent Abel et al.	arXiv	4
2026-08-27	2608.25625	RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval	Emre Kuru et al.	arXiv	4
2026-08-27	2608.14652	Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling	Yang Zhao et al.	arXiv	3
2026-08-27	2608.21839	FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling	Peiyuan Zhang et al.	arXiv	3
2026-08-27	2608.22071	Real-TurnTurk: A Multimodal Turkish Corpus for Turn-Taking Prediction	Ahmet Tuğrul Bayrak et al.	arXiv
2026-08-26	2608.24053	WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report	Junjie Zhou et al.	arXiv	73
2026-08-26	2608.24646	On-Policy Self-Distillation in Diffusion Models	Wei Zhou et al.	arXiv	68
2026-08-26	2608.23041	AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces	Sungho Park et al.	arXiv	66
2026-08-26	2608.20492	Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs	Yunheng Li et al.	arXiv	40
2026-08-26	2608.23181	CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild	Jian Yang et al.	arXiv	35
2026-08-26	2608.24876	Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses	Zhaochen Yu et al.	arXiv	32
2026-08-26	2608.15875	GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture	GigaBrain Team et al.	arXiv	27
2026-08-26	2608.24696	On-policy Distillation with Verifiable Reward	Wenze Lin et al.	arXiv	18
2026-08-26	2608.24735	Meta^n: Recursive Self-Improvement through Emergent Depth	Zae Myung Kim et al.	arXiv	18
2026-08-26	2608.24845	LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training	Andreas Hochlehnert et al.	arXiv	15
2026-08-26	2608.23566	Best Practice Critic Optimization	Penghui Qi et al.	arXiv	14
2026-08-26	2608.23918	MARS: Multi-Specialist LLM Relay System for Competitive Programming	Andrei Mikhailov et al.	arXiv	12
2026-08-26	2608.24680	Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training	Wenxuan Shen et al.	arXiv	11
2026-08-26	2608.24877	From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms	Jiangning Zhang et al.	arXiv	10
2026-08-26	2608.23740	AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace	Seonglae Cho et al.	arXiv	7
2026-08-26	2608.24569	When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows	Yiheng Sun et al.	arXiv	6
2026-08-26	2608.23670	Automata from Agent Traces: Failure and Next-Step Prediction	Seonglae Cho et al.	arXiv	6
2026-08-26	2608.24794	CAFE: Self-Improving Search Agents Need Co-Evolving Feedback	Boyang Liu et al.	arXiv	6
2026-08-26	2608.09408	DREAM Technical Report	Bin Zhang et al.	arXiv	5
2026-08-26	2608.23691	Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment	Stephen Chung et al.	arXiv	4
2026-08-26	2608.24738	TorchMorph: CUDA-accelerated Morphological Transforms	Kai Zhao	arXiv	4
2026-08-26	2608.21500	SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation	Yibo Peng et al.	arXiv	3
2026-08-26	2608.22274	Length-Adaptive Decoding for Masked Diffusion Machine Translation	Yan Zhan et al.	arXiv	3
2026-08-26	2608.24189	MemUse: Moving Memory Evaluation from Direct QA to Natural Integration in Long-Term Human-AI Conversation	Ryuichi Sumida et al.	arXiv	2
2026-08-26	2608.24763	MoTE: Mixture of Task Experts for Multi-Task Video Understanding	Muhammad Asad Ali et al.	arXiv	2
2026-08-26	2608.24882	Latent Action as Intention Enables Efficient Future Imagination for World Action Models	Xiang Li et al.	arXiv	2
2026-08-25	2608.23283	Apodex 1.1: Scaling Agentic Intelligence for Complex Work	Apodex Team et al.	arXiv	209
2026-08-25	2608.23189	EchoWM: Open and Enterable Omnimodal World Models	Songchun Zhang et al.	arXiv	62
2026-08-25	2608.23552	Prime Agent: A Self-Improving RLM Harness	Seth Karten et al.	arXiv	60
2026-08-25	2608.20958	TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming	Yibo Hu et al.	arXiv	53
2026-08-25	2608.16812	Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision	Long Cui et al.	arXiv	52
2026-08-25	2608.19567	Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion	Bowen Cui et al.	arXiv	33
2026-08-25	2608.23035	MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks	Yi Zhu et al.	arXiv	28
2026-08-25	2608.23392	Towards a Densing Law for User Representation Learning at Billion-Scale Capacity	Bin Dou et al.	arXiv	26
2026-08-25	2608.20430	RISE: Adaptive Imagination for World Action Models	Hongbo Lu et al.	arXiv	26
2026-08-25	2608.17906	AutoResearch: Insight In, Hallucination Out	Yiming Ren et al.	arXiv	25
2026-08-25	2608.23565	ReWorld: An Interactive World Model with Long-Horizon Memory	Zhifei Chen et al.	arXiv	25
2026-08-25	2608.21833	GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?	Kun Chen et al.	arXiv	18
2026-08-25	2608.23311	Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization	Xianlei Zhou et al.	arXiv	17
2026-08-25	2608.13622	ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction	Yongqi Tong et al.	arXiv	17
2026-08-25	2608.15242	LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures	Yunfei Zhang et al.	arXiv	15
2026-08-25	2608.20953	Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs	Bakbergen Ryskulov et al.	arXiv	14
2026-08-25	2608.20169	Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection	Atsuyuki Miyai et al.	arXiv	12
2026-08-25	2608.19408	Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress	Chen Yang et al.	arXiv	9
2026-08-25	2608.23200	LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks	Xiao Zhang et al.	arXiv	8
2026-08-25	2608.19741	One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows	Zhuochun Li et al.	arXiv	8
2026-08-25	2608.22872	Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors	Zhenghua Bao	arXiv	7
2026-08-25	2608.22817	Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports	Parsa Bakhtiari et al.	arXiv	6
2026-08-25	2608.22614	What AstroPT knows about galaxies, and what that can teach us about LLMs	UniverseTBD et al.	arXiv	5
2026-08-25	2608.22510	ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts	YuanHang Xiao	arXiv	5
2026-08-25	2606.13610	One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders	Minghao Luo et al.	arXiv	5
2026-08-25	2608.17336	TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration	Hanzhi Zhang et al.	arXiv	5
2026-08-25	2608.23252	The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search	Peiyang Liu et al.	arXiv	4
2026-08-25	2608.23070	From Generation to Simulation: How Far Are World Models from Being True Simulators?	Tong Wang et al.	arXiv	4
2026-08-25	2608.22856	Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA	Jingjie Ning et al.	arXiv	4
2026-08-25	2608.22876	The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models	Taebong Kim et al.	arXiv	3
2026-08-25	2608.22849	RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling	Ziyuan Wang et al.	arXiv	3
2026-08-25	2608.21455	Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection	Guray Ozgur et al.	arXiv	2
2026-08-25	2608.13914	Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning	Chun-Hua Lin et al.	arXiv	2
2026-08-25	2608.22591	WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning	Chunkai Yang et al.	arXiv	1
2026-08-25	2608.21486	EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment	Guray Ozgur et al.	arXiv
2026-08-24	2608.21156	Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence	Yuyuan Feng et al.	arXiv	68
2026-08-24	2608.16425	ParaTempo: Efficient Parallel Reasoning via Temporal Confidence	Xuteng Zhang et al.	arXiv	41
2026-08-24	2608.20910	InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter	Yunze Tong et al.	arXiv	39
2026-08-24	2608.12781	Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs	Xinming Wang et al.	arXiv	35
2026-08-24	2608.20061	Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts	Nayeon Kim et al.	arXiv	32
2026-08-24	2608.21360	OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs	Xianyun Sun et al.	arXiv	27
2026-08-24	2608.16647	Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models	Zhaoyi Li et al.	arXiv	16
2026-08-24	2608.20634	AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale	Minbyul Jeong et al.	arXiv	16
2026-08-24	2608.21439	WorldMind: Decoupled Game World Model for State-Aware NPC Behavior	Zhiyang Deng et al.	arXiv	15
2026-08-24	2608.08676	UniSpace: Unified Visual Representation and Scalable Multimodal Modeling	Jinbo Yan et al.	arXiv	12
2026-08-24	2608.20886	EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking	Enjun Du et al.	arXiv	11
2026-08-24	2608.18484	Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models	Pardis Taghavi et al.	arXiv	10
2026-08-24	2608.21134	Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs	Luka Ribar et al.	arXiv	9
2026-08-24	2608.18077	Hydra-0: Action Flow for Generalist World Modeling and Control	Hongyu Li et al.	arXiv	8
2026-08-24	2608.18184	Human-Centric Intelligence in the Era of Foundation Models: A Survey	Yang Chen et al.	arXiv	8
2026-08-24	2608.20210	Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference	Christos Koutsiaris	arXiv	8
2026-08-24	2608.20707	Towards Faithful Simulation of Human Shopping Behavior	Jiakai Tang et al.	arXiv	6
2026-08-24	2608.21278	CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment	Chengxiao Wang et al.	arXiv	6
2026-08-24	2608.21031	PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration	Chen-Yu Lin et al.	arXiv	4
2026-08-24	2608.20438	Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources	Rana Muhammad Usman et al.	arXiv	3
2026-08-24	2608.20574	FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth	Josef Chen et al.	arXiv	2
2026-08-24	2608.20364	Hadith computational science in the age of large language models: a critical narrative review	Md. Ashraful Haque et al.	arXiv	2
2026-08-21	2608.19880	EnvHarness: Awakening Static Worlds for Agent Learning	Chengsong Huang et al.	arXiv	109
2026-08-21	2608.20335	4DAnyone: Create Anyone in 4D from a Casual Monocular Video	Yudong Jin et al.	arXiv	83
2026-08-21	2608.19799	SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?	Zhipeng Xu et al.	arXiv	63
2026-08-21	2608.20336	WithEveryone: Unified Planning and Identity Grounding for Group Image Generation	Hengyuan Xu et al.	arXiv	39
2026-08-21	2608.18580	FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis	Kou Shi et al.	arXiv	34
2026-08-21	2608.20202	MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use	Mengru Wang et al.	arXiv	30
2026-08-21	2608.13120	SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback	Qianxi Yan et al.	arXiv	26
2026-08-21	2607.21596	FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills	Zeyu Ren et al.	arXiv	22
2026-08-21	2608.14022	ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models	Xinye Li et al.	arXiv	18
2026-08-21	2608.19854	Repo0: Design-Driven Zero-to-All Code Generation	Silin Chen et al.	arXiv	17
2026-08-21	2608.19758	FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving	Qihang Fan et al.	arXiv	16
2026-08-21	2608.12875	The Embedder's Dilemma: LLMs Are Better, but at What Cost?	Adnan El Assadi et al.	arXiv	11
2026-08-21	2608.16885	τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation	Xiaowei Cai et al.	arXiv	11
2026-08-21	2608.19891	EXIMO: VLM Guided Exploration of VLA Policies	Bhavya Sukhija et al.	arXiv	11
2026-08-21	2608.20281	Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization	Qian Kou et al.	arXiv	10
2026-08-21	2608.17744	Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See	Ayoub Kirouane et al.	arXiv	9
2026-08-21	2608.19936	Towards Quantifying Benchmark Optimization in ASR Models	Theo Lebryk et al.	arXiv	8
2026-08-21	2608.08466	Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses	Tailin Zhou	arXiv	7
2026-08-21	2608.18027	Chain-of-Experience for Continual LLM Improvement	Haoqin Tu et al.	arXiv	7
2026-08-21	2608.13210	NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video	Yuheng Huang et al.	arXiv	5
2026-08-21	2608.19861	PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents	Seongjae Kang et al.	arXiv	5
2026-08-21	2608.15767	TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity	Armin Steinhauser	arXiv	4
2026-08-21	2608.13547	QuoteBench: How Matched Scores Can Hide Command-Path Failures	Shangao Li et al.	arXiv	3
2026-08-21	2608.19759	GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation	Julien Merand et al.	arXiv	3
2026-08-21	2608.19776	CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning	Julien Merand et al.	arXiv	2
2026-08-21	2608.19863	Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners	Umberto Cappellazzo et al.	arXiv	2
2026-08-20	2608.16590	Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence	Xin Ding et al.	arXiv	141
2026-08-20	2608.17253	Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL	Yunhao Yang et al.	arXiv	51
2026-08-20	2608.19197	SPADE: Self-Play in Adaptive Synthetic Executable Environments	Bo Liu et al.	arXiv	50
2026-08-20	2608.17426	SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation	Keyu Tu et al.	arXiv	49
2026-08-20	2608.13558	OmniScientist: An Omni-Modal Omni-Discipline AI Scientist	Bobo Li et al.	arXiv	29
2026-08-20	2608.18940	Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis	Bogdan Zagribelnyy et al.	arXiv	23
2026-08-20	2608.18565	SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation	Yanlun Tu et al.	arXiv	21
2026-08-20	2608.14229	The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning	Anna Borisiuk et al.	arXiv	17
2026-08-20	2608.18171	Looped Language Models Improve Compositional Tool Calling	Andrei Cristian Popescu et al.	arXiv	14
2026-08-20	2608.18607	VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation	Yinming Huang et al.	arXiv	12
2026-08-20	2608.18423	FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents	Tianyou Wang et al.	arXiv	10
2026-08-20	2608.18852	SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents	Qingyao Li et al.	arXiv	9
2026-08-20	2608.18746	Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning	Jiawei Wang et al.	arXiv	8
2026-08-20	2608.15964	LLMs Get Smarter from Targeted Synthetic Multilingual Data	Ishika Agarwal et al.	arXiv	7
2026-08-20	2608.14929	Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification	Aman Singh Thakur et al.	arXiv	7
2026-08-20	2608.18701	SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset and Benchmark for Deformable-Object Manipulation	Bowen Jing et al.	arXiv	5
2026-08-20	2608.13947	Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion	Hwan Chang et al.	arXiv	4
2026-08-20	2608.15888	Bounded Agents: Delegation Security for Multi-Agent AI Systems	Xabier Muruaga	arXiv	3
2026-08-20	2608.18115	Temporal Multi-Signal Fusion for Token-Level Hallucination Detection	Igor Itkin	arXiv	3
2026-08-20	2512.14629	Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems	Yash Vishe et al.	arXiv	2
2026-08-20	2608.16490	Towards Real-Time and Adaptable LiDAR Scene Completion	Azhar Hussian et al.	arXiv	2
2026-08-20	2608.19080	SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection	Changshun Wu et al.	arXiv	2
2026-08-19	2608.16157	FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution	Shuo Yang et al.	arXiv	84
2026-08-19	2608.17310	Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements	Zhi Zheng et al.	arXiv	76
2026-08-19	2608.17271	ASI-Bench: At the Dawn of Artificial Superintelligence	Junwei Zhou et al.	arXiv	69
2026-08-19	2608.14036	Demystifying Agent Skills: Why They Work-Until They Don't	Zhiyuan Jiang et al.	arXiv	56
2026-08-19	2608.17528	Agent Lightning v1.0: Towards Harnessed Agentic RL	Zhiyuan He et al.	arXiv	35
2026-08-19	2608.17512	Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation	Hongyan Feng et al.	arXiv	32
2026-08-19	2608.12313	AVA-Encoder: Towards Agent-Native Video Representation Learning	Chuyue Li et al.	arXiv	30
2026-08-19	2608.13556	V-RAE: Rethinking Video Latent Spaces for Generation	Minghui Guo et al.	arXiv	29
2026-08-19	2608.17393	LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents	Yiming Du et al.	arXiv	27
2026-08-19	2608.17067	DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization	Tong Zhang et al.	arXiv	22
2026-08-19	2608.18063	EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing	Jiayi Song et al.	arXiv	22
2026-08-19	2608.17402	MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding	Bonan Zhang et al.	arXiv	20
2026-08-19	2608.15454	Dynamic Multi-Byte Prediction With Hierarchical Language Models	Abraham Toluwase Owodunni et al.	arXiv	19
2026-08-19	2608.17566	CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing	Fuchen Long et al.	arXiv	16
2026-08-19	2608.15008	Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents	Wei-Chieh Huang et al.	arXiv	15
2026-08-19	2608.18933	SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution	Silin Chen et al.	arXiv	14
2026-08-19	2608.17800	StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows	Liya Zhu et al.	arXiv	14
2026-08-19	2608.18076	From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation	Xingjian Wang et al.	arXiv	13
2026-08-19	2608.17286	Abra: Scaling Diffusion Image Training	Kyle Chickering et al.	arXiv	12
2026-08-19	2608.17597	HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety	Yajing Bai et al.	arXiv	11
2026-08-19	2608.17050	Cross-Model Memory Transfer via Target-Side Reader Adaptation	Mingyuan Li et al.	arXiv	8
2026-08-19	2608.05811	Energy-Guided Flow Matching	Haoyang Tong et al.	arXiv	8
2026-08-19	2608.16977	The Problem Is the Problem: Towards Scalable Mathematical Discovery	Zeyu Zheng et al.	arXiv	7
2026-08-19	2608.14221	MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement	Lushi Pu et al.	arXiv	7
2026-08-19	2608.14881	Personalized Auto-Research: Towards a True AI Co-Scientist	Bo Ni et al.	arXiv	7
2026-08-19	2608.16393	Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection	Zonghao Ying et al.	arXiv	7
2026-08-19	2608.17975	aDSL: Agentic 3D Creation via Joint Agent-Program Design	Rui-Huan Wang et al.	arXiv	7
2026-08-19	2608.16097	Unifying Graph Neural Networks Through a Common Layer Equation	Sai Karthik Navuluru et al.	arXiv	6
2026-08-19	2608.17988	GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation	Ming Qian et al.	arXiv	5
2026-08-19	2608.16002	From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents	Zhengzhao Ma et al.	arXiv	5
2026-08-19	2608.17379	PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX	Genghan Zhang et al.	arXiv	4
2026-08-19	2608.16793	PixRestore: Unified Image Restoration via Pixel Diffusion Transformer	Lingchen Sun et al.	arXiv	3
2026-08-19	2608.12944	CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation	Hamza Shafiq et al.	arXiv	1
2026-08-18	2608.15089	StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling	Ziheng Qin et al.	arXiv	107
2026-08-18	2608.16859	HarnessEval-W: Agentifying the Evaluation of Visual Worlds	Weiliang Chen et al.	arXiv	68
2026-08-18	2608.15669	Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search	Zhongwei Yu et al.	arXiv	64
2026-08-18	2608.15265	VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?	Yansong Ning et al.	arXiv	62
2026-08-18	2608.15045	MOSS-VL Technical Report	Pengyu Wang et al.	arXiv	53
2026-08-18	2608.15930	UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations	Zihan Ding et al.	arXiv	48
2026-08-18	2608.16798	ClawGym II: Exploring Black-Box RL on Agent Harness	Huatong Song et al.	arXiv	42
2026-08-18	2608.16887	An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models	Dengyang Jiang et al.	arXiv	36
2026-08-18	2608.16319	Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI	Adrian Hayler et al.	arXiv	31
2026-08-18	2608.16072	Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization	Yixuan Wang et al.	arXiv	30
2026-08-18	2608.14441	PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments	Yuhao Zhan et al.	arXiv	29
2026-08-18	2608.13900	Agentic Transaction: Towards ACID-Compliant Agent Systems	Zhaoyan Sun et al.	arXiv	28
2026-08-18	2608.16721	GenRouter: Unified Workflow Routing for Agentic Image Generation	Harold Haodong Chen et al.	arXiv	27
2026-08-18	2608.14577	HarmProfile: Characterizing Harmful Distributions in Frontier LLMs	Zhouyuan Ma et al.	arXiv	20
2026-08-18	2608.16884	Improving the matrix multiplication exponent with modern optimization and AlphaEvolve	Emilien Dupont et al.	arXiv	20
2026-08-18	2608.14783	MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling	Manwen Liao et al.	arXiv	20
2026-08-18	2608.16033	R^3-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets	Peisong Wang et al.	arXiv	17
2026-08-18	2608.15304	Understanding Cognition-Induced Risks in Agentic AI Systems	Guanchu Wang et al.	arXiv	17
2026-08-18	2608.14905	How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks	Yanlin Fei et al.	arXiv	16
2026-08-18	2608.16328	GRNEdit: Efficient General Video Editing from a New Binary-Evidence Perspective in Generative Refinement Networks	Feng Xie et al.	arXiv	13
2026-08-18	2608.16765	TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation	Haoran Wang et al.	arXiv	13
2026-08-18	2608.16391	Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs	Xiangfan Wu et al.	arXiv	13
2026-08-18	2608.16143	AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model	Kwan Yun et al.	arXiv	12
2026-08-18	2608.14718	VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding	Fan Zhang et al.	arXiv	11
2026-08-18	2608.15869	Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning	Xiaoyu Zhu et al.	arXiv	10
2026-08-18	2608.16320	StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding	Keming Wu et al.	arXiv	10
2026-08-18	2608.12898	NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents	Peng Cai et al.	arXiv	8
2026-08-18	2608.10679	ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering	Akrin Zheng et al.	arXiv	7
2026-08-18	2608.15698	ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval	Peng Chunyi et al.	arXiv	6
2026-08-18	2608.15659	WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations	Xiaojie Xu et al.	arXiv	4
2026-08-18	2608.14614	DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs	Zeyu Cao et al.	arXiv	4
2026-08-18	2608.16003	Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency	Parsa Mazaheri et al.	arXiv	4
2026-08-18	2608.15022	Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form	Parsa Mazaheri	arXiv	4
2026-08-18	2608.11947	Accuracy and Order Sensitivity Diverge Under Label-Free Strategies	Karl Hanna et al.	arXiv	2
2026-08-18	2608.14639	Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays	Bhaskar Gurram	arXiv	2
2026-08-18	2608.14606	Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents	Mantas Lukauskas et al.	arXiv	2
2026-08-18	2608.16435	Drive, Pack, Fly: The Travelling Thief Problem with Drone	Kabir Murjani et al.	arXiv	2
2026-08-18	2608.14667	Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems	Patrick Emami et al.	arXiv	2
2026-08-18	2608.06947	When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse	Yingtao Ren et al.	arXiv	2
2026-08-18	2608.15984	A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models	Kaname Yokoyama et al.	arXiv	1
2026-08-18	2608.15037	Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift	Ashish Anand Shukla et al.	arXiv	1
2026-08-18	2608.16485	HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation	Junhao Hou et al.	arXiv	1
2026-08-17	2608.14391	Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination	Shuo Liang et al.	arXiv	118
2026-08-17	2608.11341	Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence	Brian Wang et al.	arXiv	73
2026-08-17	2608.13417	Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development	Yiwei Li et al.	arXiv	59
2026-08-17	2608.14144	Self-Supervised Visual On-Policy Distillation	Yijiang Li et al.	arXiv	54
2026-08-17	2608.14277	SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning	Haonan He et al.	arXiv	36
2026-08-17	2608.14290	Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning	Kai Chen et al.	arXiv	36
2026-08-17	2608.14530	Marionette: Predicting World States, Rendering Geometry, Painting Appearance	Zian Meng et al.	arXiv	34
2026-08-17	2608.13517	DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data	Peter Schneider-Kamp et al.	arXiv	29
2026-08-17	2608.13606	MobileMem: Learning from a Year of Mobile Experiences	Xinle Deng et al.	arXiv	28
2026-08-17	2608.13040	Latent On-Policy Self-Distillation	Guibin Zhang et al.	arXiv	25
2026-08-17	2608.13667	Second Thought: Reasoning in Parallel as LLM Agents Act and Observe	Zhensu Sun et al.	arXiv	18
2026-08-17	2608.13555	HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark	Dairu Liu et al.	arXiv	18
2026-08-17	2608.13567	Modular Cognitive Architecture Emerges in Large Language Models	Pengrui Han et al.	arXiv	17
2026-08-17	2608.14071	Scaling Domain Data Repetition in LLM Pretraining	Jingwei Li et al.	arXiv	16
2026-08-17	2608.14284	PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment	Yuyang Liu et al.	arXiv	15
2026-08-17	2608.14546	CPI-Bench: A Comprehensive,Practical and Intelligent Benchmark for Real-World Image Editing	Qinye Zhou et al.	arXiv	15
2026-08-17	2608.11994	Claim-Level Reliability Assessment for Efficient Test-Time Reasoning	Sen Xu et al.	arXiv	12
2026-08-17	2608.09928	Multimodal Model Diffing for Feature Discovery and Control	Hunar Batra et al.	arXiv	11
2026-08-17	2608.11612	Dion3: Full-Stack Orthogonal Updates	Noah Amsel et al.	arXiv	11
2026-08-17	2608.14106	Forecast Collapse in Time-Series Foundation Models	Shu Wan et al.	arXiv	10
2026-08-17	2608.13545	LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure	Fanfei Li et al.	arXiv	9
2026-08-17	2608.03744	Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems	Sebastián Andrés Cajas Ordóñez et al.	arXiv	6
2026-08-17	2608.14075	A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images	Jennifer D'Souza et al.	arXiv	6
2026-08-17	2608.00220	Verifier-Induced Support Reshaping in On-Policy Optimization	Shaohang Wei et al.	arXiv	6
2026-08-17	2608.13987	Nanbeige4.2-3B on Apple Silicon: Fixing Deployment Bugs and Decreasing Looped Transformer Memory Overhead	John T. Halloran	arXiv	5
2026-08-17	2608.12209	Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction	Zhongbin Guo et al.	arXiv	5
2026-08-17	2608.12571	Is this Citation on Point?	Apurv Verma	arXiv	4
2026-08-17	2608.13760	Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models	Jean de Dieu Nyandwi et al.	arXiv	4
2026-08-17	2608.10835	UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations	Dvir Samuel et al.	arXiv	4
2026-08-17	2608.09209	UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers	Chidaksh Ravuru et al.	arXiv	2
2026-08-17	2608.13410	Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings	Mirko Tritella et al.	arXiv	1
2026-08-17	2608.14138	SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation	Jinsheng Quan et al.	arXiv	1
2026-08-14	2608.07545	DarwinX: Evolving Agent Harnesses Through Natural Selection	Yifan Zhang et al.	arXiv	97
2026-08-14	2608.13546	Alaya-EVOKE: From Linear-Scaling Supervision to Endless World	Yuanyang Yin et al.	arXiv	76
2026-08-14	2608.13505	Intern-S2-Preview: Scientific Agentic Foundation Model	Lei Bai et al.	arXiv	69
2026-08-14	2608.13560	AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design	Yaxin Luo et al.	arXiv	59
2026-08-14	2608.13489	DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation	DreamX Team et al.	arXiv	54
2026-08-14	2608.06867	LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers	Tao Feng et al.	arXiv	49
2026-08-14	2608.13552	PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives	Kaixin Ding et al.	arXiv	42
2026-08-14	2608.12743	Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence	Haokai Zhang et al.	arXiv	26
2026-08-14	2608.08975	How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review	Ming Li et al.	arXiv	25
2026-08-14	2608.12149	Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus	Zunhai Su et al.	arXiv	22
2026-08-14	2608.11745	LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time	Yuxuan Zhang et al.	arXiv	17
2026-08-14	2608.08888	Full-bandwidth transformer	Xi Wang et al.	arXiv	15
2026-08-14	2608.11752	UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos	Yuxuan Zhang et al.	arXiv	14
2026-08-14	2608.13049	H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models	Dingyi Rong et al.	arXiv	14
2026-08-14	2608.13391	Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation	Hmrishav Bandyopadhyay et al.	arXiv	11
2026-08-14	2608.10538	SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models	Chenhao Dang et al.	arXiv	9
2026-08-14	2608.02870	Maglev: Sliding Recurrent Memory	Bo Liu et al.	arXiv	7
2026-08-14	2608.08020	Thought-Level Beam Search for Reasoning	Lijie Yang et al.	arXiv	7
2026-08-14	2608.07193	An AI4AI Framework for Visual Token Pruning	Zhen Liu et al.	arXiv	7
2026-08-14	2608.12990	LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation	Dongfang Li et al.	arXiv	7
2026-08-14	2608.13430	Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity	Irina Proskurina et al.	arXiv	5
2026-08-14	2607.29211	Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning	Xinyan Guan et al.	arXiv	5
2026-08-14	2608.11660	Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing	Tianci Liu et al.	arXiv	4
2026-08-14	2608.12440	Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review	Joel Abenhaim	arXiv	4
2026-08-14	2608.12997	PixSDS: Why Latent SDS Makes Noisy Pixels	Vsevolod Skorokhodov	arXiv	4
2026-08-14	2608.06914	RibAssist 3D: Biplanar Rib-Fracture Detection, Addressing, and Selective 3D Localization from CT-Derived Projections	Kabila Haile Soboka	arXiv	3
2026-08-14	2608.09158	From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs	Yuanhe Zhang et al.	arXiv	2
2026-08-14	2608.11951	TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement	Karim Aly et al.	arXiv	2
2026-08-14	2608.08606	Mitigating Gender Bias in English to Romanian Machine Translation	Ioana Grigore et al.	arXiv	1
2026-08-14	2608.12773	CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers	Ebenezer Tarubinga	arXiv	1
2026-08-13	2608.12307	AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses	Cheng Qian et al.	arXiv	107
2026-08-13	2608.12036	Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence	Mengru Wang et al.	arXiv	90
2026-08-13	2608.11924	Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill	Zhuoyang Qian et al.	arXiv	62
2026-08-13	2608.12314	StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization	Yuyang Yin et al.	arXiv	28
2026-08-13	2608.00677	OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution	Yunhao Chen et al.	arXiv	27
2026-08-13	2608.08160	Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives	Yingpeng Ma et al.	arXiv	23
2026-08-13	2608.05604	SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries	Xingyu Tan et al.	arXiv	21
2026-08-13	2608.10708	Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models	Seokhyun Youn et al.	arXiv	16
2026-08-13	2608.09926	Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning	Haodong Li et al.	arXiv	15
2026-08-13	2608.11350	Self-Evolving Embodied Agents via Skill-Harness Evolution	Peidong Wang et al.	arXiv	15
2026-08-13	2608.11216	AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research	Marjan Moodi et al.	arXiv	14
2026-08-13	2608.11878	ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents	Yutao Mou et al.	arXiv	13
2026-08-13	2608.11562	From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection	Zepeng Wang et al.	arXiv	10
2026-08-13	2608.09805	Parameter Exploration for RLVR via Variational Learning	Vatsal Venkatkrishna et al.	arXiv	8
2026-08-13	2608.10450	Persistent Recursive Worlds Enable Autonomous Software Evolution	Beichen Huang et al.	arXiv	8
2026-08-13	2608.11215	Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop	Igor Itkin	arXiv	7
2026-08-13	2608.10615	Simplex Relaxation for Discrete Diffusion	Jinya Sakurai et al.	arXiv	7
2026-08-13	2608.06270	The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images	Zhiheng Wang et al.	arXiv	7
2026-08-13	2608.11616	MBA: Multimodal Benchmark and Agents for Real-World Business Ideation	Hojun Choi et al.	arXiv	7
2026-08-13	2608.11367	Gaze Target Estimation Anywhere with Concepts	Xu Cao et al.	arXiv	5
2026-08-13	2608.11274	Agent Safety Should Be a Runtime Contract	Albus W. Ng et al.	arXiv	5
2026-08-13	2608.06729	AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models	Guiyu Zhao et al.	arXiv	4
2026-08-13	2608.08107	NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs	Jiayue Jin et al.	arXiv	4
2026-08-13	2608.12836	From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options	Obed Junias et al.	arXiv	3
2026-08-13	2608.11045	ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization	He-Yen Hsieh et al.	arXiv	3
2026-08-13	2608.12123	Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control	Josef Liyanjun Chen	arXiv	3
2026-08-13	2608.11574	Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands	Ryosei Hara et al.	arXiv	3
2026-08-12	2608.10299	Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design	Qing Zong et al.	arXiv	130
2026-08-12	2608.10915	ComBodied Agents: a New Paradigm of Human-Centric Agentic AI	Qianggang Ding et al.	arXiv	94
2026-08-12	2608.10744	Beyond Pixels: From Video Priors to 4D Worlds	Zihao Liu et al.	arXiv	74
2026-08-12	2607.27749	Articulated Object Reconstruction from Rest-State Observation	Daeun Lee et al.	arXiv	47
2026-08-12	2608.07645	Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution	Changzhi Liu et al.	arXiv	22
2026-08-12	2608.11205	AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss	Mingju Gao et al.	arXiv	21
2026-08-12	2608.10875	VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?	Xiaohongshu Inc	arXiv	14
2026-08-12	2608.11079	SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure	Xiaofan Bai et al.	arXiv	12
2026-08-12	2608.10720	Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence	Haoyu Zhang et al.	arXiv	9
2026-08-12	2608.10812	Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation	Chris Han et al.	arXiv	8
2026-08-12	2608.08627	UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models	Lei Xin et al.	arXiv	7
2026-08-12	2608.10692	SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information	Junjie Ye et al.	arXiv	7
2026-08-12	2608.07458	CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG	Gyuwan Kim et al.	arXiv	6
2026-08-12	2608.10628	InSight-doc: Agentic Visual Perception for Long-Document Understanding	Kaican Li et al.	arXiv	6
2026-08-12	2608.08814	360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents	Kenta Watanabe et al.	arXiv	6
2026-08-12	2608.09900	Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness	Tadanobu Chuyo Kamijo et al.	arXiv	6
2026-08-12	2608.10636	DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation	Zhuchenyang Liu et al.	arXiv	6
2026-08-12	2608.08389	Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents	Harshitha Kolukuluru et al.	arXiv	6
2026-08-12	2608.10366	DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?	Mizanur Rahman et al.	arXiv	6
2026-08-12	2608.03216	iFAN: Inference-Aware Learning for Plain Mask Transformers	Fang Li et al.	arXiv	5
2026-08-12	2608.08119	TSDS-Toolbox: A Toolbox for Measuring Time-Series Dataset Similarity	Yen-Ku Liu et al.	arXiv	5
2026-08-12	2607.27670	JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles	Shawn Li et al.	arXiv	4
2026-08-12	2608.10288	Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference	Burc Gokden	arXiv	2
2026-08-11	2608.09888	BDH-CQ: In-Context Learning with Recurrent Latent Reasoning	Björn Engdahl et al.	arXiv	745
2026-08-11	2608.06296	On-Policy Self-Distillation without Any Supervision	Yijiang Li et al.	arXiv	125
2026-08-11	2608.09867	Stealing Reasoning Traces from Proprietary LLM APIs	Alexander Panfilov et al.	arXiv	119
2026-08-11	2608.09819	Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA	Mind Lab et al.	arXiv	113
2026-08-11	2608.08311	Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution	Anton Razzhigaev et al.	arXiv	91
2026-08-11	2608.09802	SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring	Yuling Shi et al.	arXiv	73
2026-08-11	2608.09119	Motif 3: Technical Report	Junghwan Lim et al.	arXiv	46
2026-08-11	2608.07169	Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory	Taeil Kim et al.	arXiv	45
2026-08-11	2608.07565	What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems	Zhijing Zhang et al.	arXiv	26
2026-08-11	2608.06751	Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation	Kuan Xing et al.	arXiv	25
2026-08-11	2608.08097	OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching	Can Xiao et al.	arXiv	23
2026-08-11	2608.07594	Scaling Inherently Interpretable Language Models	Guide Labs Team et al.	arXiv	19
2026-08-11	2608.08621	Business Arena: Benchmarking LLM Agents in a Realistic Marketplace	Yijun Pan et al.	arXiv	18
2026-08-11	2608.09096	Evo-Bench: Can Language Models Improve Agent Harness?	Lisheng Huang et al.	arXiv	18
2026-08-11	2608.09873	Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains	Diandian Zhang et al.	arXiv	15
2026-08-11	2608.04419	SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation	Zikun Qu et al.	arXiv	15
2026-08-11	2608.09853	RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance	Dongchi Huang et al.	arXiv	14
2026-08-11	2608.08021	Evidence-RL: Towards Evidence-intensive Visual Reasoning	Haojie Huang et al.	arXiv	14
2026-08-11	2608.07346	A^2E : An End-to-End Agent Auditing Engine	Haoning Wang et al.	arXiv	10
2026-08-11	2608.02508	RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States	Yi Yang et al.	arXiv	10
2026-08-11	2608.03499	WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks	Prince Zizhuang Wang et al.	arXiv	7
2026-08-11	2608.09043	Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization	Hyangsuk Min et al.	arXiv	5
2026-08-11	2608.09420	Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation	Bo Wang et al.	arXiv	5
2026-08-11	2608.06065	The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents	Weiwei Li et al.	arXiv	4
2026-08-11	2608.08156	A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization	Víctor Gallego	arXiv	4
2026-08-11	2607.27637	MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models	Wenjie Zhu et al.	arXiv	4
2026-08-11	2608.06614	Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval	Linhai Ma et al.	arXiv	4
2026-08-11	2608.06111	Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers	Haris Riaz et al.	arXiv	3
2026-08-11	2608.07463	MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation	Youjun Zhao et al.	arXiv	3
2026-08-11	2608.03887	Omega-S: A Functional Resilience Index for LLM Fine-Tuning	Alberto Acedo	arXiv	3
2026-08-11	2608.08722	Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure	Víctor Gallego	arXiv	3
2026-08-11	2608.05136	The Loss Does Not See the Basis, but Adam Does	Devender Singh	arXiv	3
2026-08-11	2608.08285	Ego-OSCAR: Egocentric Open source Stereo CAptuRe System	Gunjan Paul et al.	arXiv	3
2026-08-11	2608.09848	CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems	Aimilios Hadjiliasi et al.	arXiv	3
2026-08-11	2608.08477	VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use	Juan S. Santillana	arXiv	2
2026-08-11	2608.09766	Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness	Pinzhen Chen et al.	arXiv	2
2026-08-11	2608.08786	SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification	Wenyao Cui et al.	arXiv	2
2026-08-11	2608.07886	Vision-Language Grounding as Bidirectional Concept Correspondence	Jieyu Zhang et al.	arXiv	2
2026-08-10	2608.04205	MatrAIx: Simulating the World with 8.3 Billion Persona Agents	Xiaomin Li et al.	arXiv	58
2026-08-10	2608.03573	SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs	Kejian Zhu et al.	arXiv	56
2026-08-10	2608.03571	Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning	Kejian Zhu et al.	arXiv	41
2026-08-10	2608.07468	SimWAM: A Simple World Action Model for End-to-End Autonomous Driving	Zongchuang Zhao et al.	arXiv	27
2026-08-10	2608.05224	Small Foundation Models of Human Cognition and Behaviour	Nick Oh et al.	arXiv	21
2026-08-10	2608.07051	YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family	Xu Lin et al.	arXiv	21
2026-08-10	2608.05703	StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding	Xichen Zhang et al.	arXiv	18
2026-08-10	2608.06113	DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds	Kishanthan Thangarajah et al.	arXiv	17
2026-08-10	2607.23379	When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles	Tobias Bersia et al.	arXiv	17
2026-08-10	2608.03796	Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss	Bakbergen Ryskulov et al.	arXiv	16
2026-08-10	2608.07222	Skaling: Chinchilla's Exponents Meet Kaplan's Coupling	Mathurin Videau et al.	arXiv	15
2026-08-10	2608.07408	Addressable Memory for Video World Models	Xindi Wu et al.	arXiv	15
2026-08-10	2608.02148	Douyin Multimodal Embedding Model Technical Report	Haonan Chen et al.	arXiv	14
2026-08-10	2608.04569	Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression	Zhengpei Hu et al.	arXiv	12
2026-08-10	2607.26178	DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues	Takyoung Kim et al.	arXiv	11
2026-08-10	2608.07110	Modular TTT: Rethinking Test-Time Training as Composable Modules	Bohao Tang et al.	arXiv	11
2026-08-10	2608.06865	Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection	Xuechao Zou et al.	arXiv	10
2026-08-10	2608.05597	Uncertainty-Aware World Model for Aerial Image-Goal Navigation	Deyi Zhu et al.	arXiv	10
2026-08-10	2608.06640	Characterizing the Quality Profile of AI-Generated C++ in Production	Michael Tran et al.	arXiv	10
2026-08-10	2608.00675	Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors	Alexander Scheinker	arXiv	9
2026-08-10	2608.06714	The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows	Junbo Li et al.	arXiv	9
2026-08-10	2608.02831	Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning	Fangxu Yu et al.	arXiv	8
2026-08-10	2608.06756	Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence	Ying Chen et al.	arXiv	5
2026-08-10	2608.05219	When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents	Junzhuo Liu et al.	arXiv	5
2026-08-10	2607.26657	Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control	Weili Zeng et al.	arXiv	4
2026-08-10	2608.01310	FATE: Frame-Level Audio-Visual Temporal Embedding	Kaisi Guan et al.	arXiv	4
2026-08-10	2608.06013	OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception, Understanding, and Interaction	Jiahao Huang et al.	arXiv	4
2026-08-10	2608.07341	Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination	Ruijie Hou et al.	arXiv	4
2026-08-10	2608.06485	Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events	Ming Wang et al.	arXiv	4
2026-08-10	2608.04314	Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle	Jiaming Zhang et al.	arXiv	3
2026-08-10	2603.18846	Towards Interpretable Foundation Models for Retinal Fundus Images	Samuel Ofosu Mensah et al.	arXiv	3
2026-08-10	2608.06501	Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding	Ming Wang et al.	arXiv	3
2026-08-10	2606.00152	PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say	Mingxuan Zhang et al.	arXiv	3
2026-08-10	2608.04302	CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models	Mukhtiar Ali et al.	arXiv	2
2026-08-10	2607.27945	Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting	Kuo-Chung Peng et al.	arXiv	2
2026-08-07	2608.05987	AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning	Zi-Han Wang et al.	arXiv	82
2026-08-07	2607.28609	OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models	Qiushi Sun et al.	arXiv	67
2026-08-07	2608.01481	Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval	Ilia Semenkov et al.	arXiv	66
2026-08-07	2608.05248	WorldClaw: Agentic 3D Open-World Generation at Scale	Chunchao Guo et al.	arXiv	66
2026-08-07	2608.06197	EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning	Zishan Xu et al.	arXiv	39
2026-08-07	2608.06020	From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models	Jiale Han et al.	arXiv	25
2026-08-07	2608.05747	GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?	Qifeng Zhang et al.	arXiv	25
2026-08-07	2608.05138	Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains	Ayoub Kirouane et al.	arXiv	24
2026-08-07	2608.03451	DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces	Boyan Li et al.	arXiv	19
2026-08-07	2608.06216	Continual Learning in Transition	Zhiyan Hou et al.	arXiv	18
2026-08-07	2608.05369	World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation	Yuhao Pan et al.	arXiv	18
2026-08-07	2608.05137	SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding	Yue Zhang et al.	arXiv	17
2026-08-07	2608.06060	Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval	Zelong Sun et al.	arXiv	17
2026-08-07	2608.05631	ChronoVision: Temporal Reasoning via Latent State Reconstruction	Yifan Shen et al.	arXiv	17
2026-08-07	2608.05798	KVAE: Family of Tokenizers for Multimodal Generative Models	Andrey Shutkin et al.	arXiv	16
2026-08-07	2608.06301	HarnessOpt-Bench: Evaluating LLMs at Harness Optimization	Varun Ursekar et al.	arXiv	15
2026-08-07	2608.05850	MameLoshnLM: Yiddish Language Model and Evaluation Benchmark	Uri Katz et al.	arXiv	14
2026-08-07	2608.05565	EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal	Feier Wu et al.	arXiv	14
2026-08-07	2608.06352	CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks	Fanzhe Meng et al.	arXiv	14
2026-08-07	2608.06146	PaDoc: Layout-Grounded Parallel Decoding for Document Parsing	Hao Yu et al.	arXiv	12
2026-08-07	2608.05802	On-Policy Delta Distillation for Multilingual Math Reasoning	Byeongho Heo et al.	arXiv	10
2026-08-07	2608.05784	Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay	Nossa Iyamu	arXiv	9
2026-08-07	2608.06257	MASS: Multiplayer World Models with Authoritative Shared State	Ziqi Cai et al.	arXiv	9
2026-08-07	2608.05424	Invisible Shortcuts: Why Vision Encoders Know Your Camera	Vladan Stojnić et al.	arXiv	9
2026-08-07	2608.01492	GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization	Baihan Yang et al.	arXiv	6
2026-08-07	2608.01851	Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills	Gaytri Jena et al.	arXiv	5
2026-08-07	2608.04956	ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing	Xu Guo et al.	arXiv	5
2026-08-07	2608.01049	FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds	Kapil Wanaskar et al.	arXiv	4
2026-08-07	2608.05785	Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation	Tirth Bhatt et al.	arXiv	3
2026-08-07	2608.06374	DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation	Junfeng Li et al.	arXiv	1
2026-08-06	2608.05466	Recursive Synthesis for Long-Horizon Terminal Tasks	Zhongzhi Li et al.	arXiv	80
2026-08-06	2608.05000	Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes	Junlin Han et al.	arXiv	60
2026-08-06	2608.04436	ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation	Jiahao Zhao et al.	arXiv	58
2026-08-06	2608.05102	ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment	Yijun Lu et al.	arXiv	35
2026-08-06	2608.05013	OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents	Jingsheng Zheng et al.	arXiv	35
2026-08-06	2608.04570	The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads	Yushi Sun et al.	arXiv	35
2026-08-06	2608.05070	HelloWorld: Enabling Socially Interactive Characters in Video World Models	Liangyang Ouyang et al.	arXiv	34
2026-08-06	2608.04505	K-EXAONE 2.0 Technical Report	Eunbi Choi et al.	arXiv	24
2026-08-06	2608.05139	Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning	Yinghui He et al.	arXiv	23
2026-08-06	2608.03764	GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks	Leijun Zhou et al.	arXiv	22
2026-08-06	2608.02580	Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data	Ye Wang et al.	arXiv	21
2026-08-06	2608.03632	When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation	Yinuo Jiang et al.	arXiv	19
2026-08-06	2608.04397	NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap	Dasol Choi et al.	arXiv	18
2026-08-06	2608.00782	Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance	Zhuowen Han et al.	arXiv	13
2026-08-06	2608.02162	Lossless Tensor Compression as Program Synthesis	Jieke Shi et al.	arXiv	12
2026-08-06	2607.27853	FinanceHarness: Autonomous Financial Deep Research Framework	Yijia Xiao et al.	arXiv	11
2026-08-06	2607.24821	AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities	Yuqing Wen et al.	arXiv	11
2026-08-06	2608.04574	When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents	Yushi Sun et al.	arXiv	11
2026-08-06	2608.04964	WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models	Bohai Gu et al.	arXiv	10
2026-08-06	2608.04530	FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory	Zhuoran Zhang et al.	arXiv	9
2026-08-06	2608.05131	OPD-V: Visual On-Policy Self-Distillation with Modality Balance	Aniri et al.	arXiv	9
2026-08-06	2608.03392	Self-Evolving Coding Agents	Hao Zhou et al.	arXiv	8
2026-08-06	2607.28048	SKILL-KD: Contrastive Skill Distillation for LLM Agents	Qiming Shi et al.	arXiv	8
2026-08-06	2608.04349	Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models	Siming Fu et al.	arXiv	8
2026-08-06	2607.21735	What AI Red-Team Evaluations Can and Cannot Prove	Bandana Kaur	arXiv	5
2026-08-06	2608.04926	Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning	Xuehang Guo et al.	arXiv	4
2026-08-06	2608.05042	BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation	Peiyan Li et al.	arXiv	4
2026-08-06	2608.04701	UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models	Haiyang Zhou et al.	arXiv	4
2026-08-06	2608.04244	SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models	Sirun Li et al.	arXiv	3
2026-08-06	2608.03207	DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack	Hoseong Tae et al.	arXiv	3
2026-08-06	2608.05108	Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming	Yanting Wang et al.	arXiv	3
2026-08-06	2608.04378	Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation	Scott H. Hawley	arXiv	2
2026-08-06	2608.03836	Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers	Sajjad Khan	arXiv	2
2026-08-06	2607.22143	TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex	Yuliang Yan et al.	arXiv	2
2026-08-05	2608.03974	JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion	Yicheng Xiao et al.	arXiv	92
2026-08-05	2607.28956	MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations	Qiming Shi et al.	arXiv	85
2026-08-05	2608.02602	AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling	Jiajun Liang et al.	arXiv	71
2026-08-05	2608.02711	Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing	Junliang Ye et al.	arXiv	46
2026-08-05	2608.02713	Quo Vadis, World Modeling?	Yu Yang et al.	arXiv	34
2026-08-05	2608.03979	Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent	Zhen Fang et al.	arXiv	31
2026-08-05	2608.01837	PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning	Chunji Lv et al.	arXiv	27
2026-08-05	2608.03457	LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models	Fengqi Zhu et al.	arXiv	24
2026-08-05	2608.04003	PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents	Shuhan Xue et al.	arXiv	23
2026-08-05	2607.28661	Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements	Xinke Tong et al.	arXiv	19
2026-08-05	2608.03812	OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models	Wanshun Su et al.	arXiv	17
2026-08-05	2608.01127	MiniWorld: Democratizing the Training of Video World Models from Scratch	Yian Zhao et al.	arXiv	16
2026-08-05	2608.03971	UniWorld-Design: From Pixel Generation to Layer-Native Design	Zongjian Li et al.	arXiv	13
2026-08-05	2608.03316	Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging	Siming Fu et al.	arXiv	13
2026-08-05	2608.02589	CAPEval: A Decoupled Caption Evaluation across Understanding and Generation	Zhipeng Liu et al.	arXiv	12
2026-08-05	2608.01247	RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction	Changwoo Baek et al.	arXiv	11
2026-08-05	2608.03509	SkillJack: Persistent Skill Backdoors in Self-Evolving Agents	Zonghao Ying et al.	arXiv	11
2026-08-05	2608.00371	Decoding Children's Gait Behavior	Yifan Shen et al.	arXiv	10
2026-08-05	2608.03874	ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?	Tianyi Guan et al.	arXiv	10
2026-08-05	2607.26451	ExplainBench: Evaluating Code Explanations from Agents	Zhiyuan Pan et al.	arXiv	9
2026-08-05	2607.00482	Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking	Chia-Hsuan Lee et al.	arXiv	8
2026-08-05	2608.03994	When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings	Christopher Schröder et al.	arXiv	8
2026-08-05	2608.04007	TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning	Changle Qu et al.	arXiv	7
2026-08-05	2608.02703	ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads	Şuayp Talha Kocabay et al.	arXiv	6
2026-08-05	2608.03972	ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning	Jinhe Bi et al.	arXiv	6
2026-08-05	2608.02791	Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation	Jiazhen Liu et al.	arXiv	6
2026-08-05	2608.03756	LegalPincite: Multi-level Legal Information Retrieval Dataset	Theresia Veronika Rampisela et al.	arXiv	5
2026-08-05	2608.03507	ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels	Gagan Bhatia et al.	arXiv	5
2026-08-05	2608.00730	Push-Wiper: Toward General-Purpose Robotic Cleaning across Varied Stains and Surfaces with Segmented Pushing Trajectories	Renhao Lu et al.	arXiv	5
2026-08-05	2608.02833	CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning	Xuehang Guo et al.	arXiv	4
2026-08-05	2608.03419	Multi-Task Multi-Frame Visual Piano Transcription	Yonghyun Kim et al.	arXiv	4
2026-08-05	2608.03700	When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills	Yongli Xiang et al.	arXiv	4
2026-08-05	2608.02392	GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience	Sitong Gong et al.	arXiv	4
2026-08-05	2608.03506	When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs	Omatharv Bharat Vaidya et al.	arXiv	3
2026-08-05	2607.28993	ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts	Mingxin Wang et al.	arXiv	3
2026-08-05	2608.02751	Search, Inspect, Fetch: Exploiting Boolean Retrieval for Deep-Research Agents	Shuai Wang et al.	arXiv	2
2026-08-05	2608.02218	PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs	Haojie Hu et al.	arXiv	2
2026-08-04	2608.01964	LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks	Ziyu Ma et al.	arXiv	139
2026-08-04	2608.02437	InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis	Jiawei Wang et al.	arXiv	74
2026-08-04	2608.02023	SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks	Yu Zhang et al.	arXiv	66
2026-08-04	2608.01678	Progressive Agent Skill Generation via Reinforcement Learning	Junhao Shen et al.	arXiv	52
2026-08-04	2607.28590	VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation	Kangning Zhang et al.	arXiv	41
2026-08-04	2608.00799	CADENA: Stepwise CAD Reverse Engineering	Soslan Kabisov et al.	arXiv	38
2026-08-04	2608.02583	UEmbed: Unified Sparse and Dense Multimodal Embeddings	Tingyu Song et al.	arXiv	38
2026-08-04	2608.00146	DiffusionGemma Technical Report	DiffusionGemma Team et al.	arXiv	36
2026-08-04	2608.01735	DAPD: Dual-Anchored Policy Distillation	Jianyu Wu et al.	arXiv	35
2026-08-04	2608.01755	Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs	Zixuan Huang et al.	arXiv	33
2026-08-04	2608.02603	WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity	Yuxue Yang et al.	arXiv	31
2026-08-04	2608.02287	SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation	Zelin Tan et al.	arXiv	25
2026-08-04	2607.29613	WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning	Senyu Fei et al.	arXiv	23
2026-08-04	2607.25614	MemSFT: Mitigating Alignment Tax with an External Parametric Memory	Jiarui Wang et al.	arXiv	22
2026-08-04	2607.28887	To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing	Amir M. Ebrahimi et al.	arXiv	21
2026-08-04	2608.00155	AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?	Dong Yan et al.	arXiv	19
2026-08-04	2608.02499	SWE-Touch: Benchmarking Coding Agents When Users Touch the Code	Yuqiao Tan et al.	arXiv	19
2026-08-04	2608.02585	GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning	Zhaoxin Yu et al.	arXiv	18
2026-08-04	2608.01628	Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations	Zhixue Fang et al.	arXiv	16
2026-08-04	2608.00079	LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation	Rongxiang Zhang et al.	arXiv	15
2026-08-04	2608.01185	3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering	Changwoo Baek et al.	arXiv	14
2026-08-04	2608.01827	DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents	Huanyao Zhang et al.	arXiv	13
2026-08-04	2607.29377	Zero-Mem: Zero-Token Memory Operations for LLM Agents	Yilin Xiao et al.	arXiv	12
2026-08-04	2608.01397	SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space	Ruiteng Zhao et al.	arXiv	11
2026-08-04	2608.00486	DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents	Tongsheng Ding et al.	arXiv	11
2026-08-04	2608.01973	Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis	Lingwei Dang et al.	arXiv	11
2026-08-04	2607.28802	Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures	Harsh Raj et al.	arXiv	9
2026-08-04	2607.27042	GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding	Jiale Chen et al.	arXiv	8
2026-08-04	2608.01954	StyleForge: Indoor Furniture Styling by Counterfactual Reasoning in a Hypergraph Field	Lingwei Dang et al.	arXiv	8
2026-08-04	2607.29241	RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems	Haoran Ling et al.	arXiv	7
2026-08-04	2608.01862	Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge	Xiaofeng Shi et al.	arXiv	6
2026-08-04	2608.00440	Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis	Zhishan Zou	arXiv	6
2026-08-04	2608.02358	ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step	Vernon Toh et al.	arXiv	6
2026-08-04	2607.26326	Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models	Jiaang Li et al.	arXiv	5
2026-08-04	2607.29122	A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples	Zixuan Fu et al.	arXiv	5
2026-08-04	2608.01462	Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI	Quang Bui et al.	arXiv	4
2026-08-04	2607.26848	ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures	Fahad Ahmed et al.	arXiv	4
2026-08-04	2607.23693	Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV	Zefeng Cai et al.	arXiv	3
2026-08-04	2608.02315	GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation	Gaetano Chiriaco et al.	arXiv	3
2026-08-04	2608.00574	Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts	Ziang Wu et al.	arXiv	3
2026-08-03	2607.23802	From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement	Qinsi Wang et al.	arXiv	78
2026-08-03	2607.23782	N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens	NeoteAI Team et al.	arXiv	67
2026-08-03	2607.27201	Mental World Modeling	Hao Fei et al.	arXiv	54
2026-08-03	2607.28675	Meshy T2: Fast Native Mesh Generation with Flow Matching	Jiale Xu et al.	arXiv	52
2026-08-03	2607.23783	N_0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation	NeoteAI Team et al.	arXiv	48
2026-08-03	2607.26611	Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants	Zijian Xu et al.	arXiv	32
2026-08-03	2607.29679	Scaling Properties of Text Conditioning in Visual Generation	Zilong Chen et al.	arXiv	30
2026-08-03	2607.29209	SAF-OPD: Stable Advantage Fusion for On-Policy Distillation	Yifan Ding et al.	arXiv	26
2026-08-03	2607.28617	AISPA: User-Centric System Prompt Auditing for Large Language Model Applications	Xiangning Lin et al.	arXiv	25
2026-08-03	2607.28415	QQWorld: Quantile-Quantile Matching for World Model Regularization	Zhoushun Yu et al.	arXiv	20
2026-08-03	2607.26246	Weak-to-Strong On-Policy Distillation	Fangxu Yu et al.	arXiv	19
2026-08-03	2607.27924	ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow	Dongxiu Liu et al.	arXiv	14
2026-08-03	2607.29677	ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction	Boyang Zhang et al.	arXiv	14
2026-08-03	2607.18082	Enhancing Rubric-based RL via Self-Distillation	Mingxuan Xia et al.	arXiv	12
2026-08-03	2607.28229	EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents	Luigi Sigillo et al.	arXiv	11
2026-08-03	2607.27888	Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning	Qiangqiang He et al.	arXiv	7
2026-08-03	2607.26991	RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models	Derek Ming Siang Tan et al.	arXiv	6
2026-08-03	2607.28443	One Future, Every Robot: Label-Efficient Collective-State Prediction with Decentralized JEPA	Alan-Barsag Gazzaev et al.	arXiv	6
2026-08-03	2607.27951	Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs	Pingyu Wu et al.	arXiv	6
2026-08-03	2607.15820	In the Driver's Seat: A Multi-Company Study on the Reality of Autonomous Driving System Testing	Qunying Song et al.	arXiv	5
2026-08-03	2607.28478	Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning	Zheng Wu et al.	arXiv	5
2026-08-03	2607.29025	Evaluation-Verification Reward for Consistent Multi-Reference Image Editing	Yingmao Miao et al.	arXiv	5
2026-08-03	2607.29684	Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark	Muyao Niu et al.	arXiv	4
2026-08-03	2607.28996	SULAND v2: A Refined RGB Dataset and Deep Learning Object Detection Benchmark for UAV/UGV-Based SUrface LANDmine Detection Under Domain Shift	Sagar Lekhak et al.	arXiv	4
2026-08-03	2607.26654	Constitutional Midtraining: Content Presence Drives Alignment Gains	Desiree Cho et al.	arXiv	3
2026-08-03	2607.25388	SGTP: Sampling-based Game-Theoretic Planning for Real-Time Multi-Vehicle Autonomous Racing	Zhouheng Li et al.	arXiv	3
2026-08-03	2607.27851	Beyond Feeling Better: Capability-Sustaining Emotional Dialogue as a Longitudinal Research Paradigm	Ming Wang et al.	arXiv	2