| 2026-11-19 | 2611.24154 | Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development | Xirui Jiang et al. | arXiv | 28 | |
| 2026-11-19 | 2611.24059 | Replay, Don't Resample: Off-Policy Consolidation of Long-Horizon RL Experts | Zhenrui Yue et al. | arXiv | 4 | |
| 2026-11-18 | 2611.21791 | Regularized Score Centering | Hao Bai et al. | arXiv | 4 | |
| 2026-11-17 | 2611.19649 | LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers | Siqi Zhu et al. | arXiv | 4 | |
| 2026-11-10 | 2611.11994 | EmoHarness: Boosting Multimodal Emotion Understanding with Meta-Harness Evolving | Fenghai Li et al. | arXiv | 2 | |
| 2026-10-25 | 2610.34073 | Memory Tax: Dissecting the Net Value of Agent Memory | Xuan He et al. | arXiv | 29 |  |
| 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 | 2610.29927 | Your Benchmark Is an Empirical Measure Over Difficulty | Yifan Sun et al. | arXiv | 18 | |
| 2026-10-20 | 2610.22894 | Competence-Based Evaluation of Logical Reasoning in Large Language Models | Jize Jiang et al. | arXiv | 4 | |
| 2026-10-16 | 2610.21412 | JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs | Kunlun Zhu et al. | arXiv | 25 | |
| 2026-10-14 | 2610.18738 | Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization | Hao Bai et al. | arXiv | 3 | |
| 2026-10-14 | 2610.04851 | CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery | Tao Feng et al. | arXiv | 3 | |
| 2026-10-09 | 2610.04977 | Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation | Jerry Wang et al. | arXiv | 13 | |
| 2026-10-08 | 2610.09457 | DSReg: Provably Recovering Individual World Latents without Reconstruction | Yujia Zheng et al. | arXiv | 3 | |
| 2026-10-08 | 2609.38680 | ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images | Shubhang Bhatnagar et al. | arXiv | 1 | |
| 2026-10-07 | 2610.07510 | Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training | Qiusi Zhan et al. | arXiv | 13 | |
| 2026-10-06 | 2610.04292 | LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures | Jiateng Liu et al. | arXiv | 34 | |
| 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 | 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 | |
| 2026-10-02 | 2610.02193 | Hierarchical Continuous Diffusion Language Models | Hui Ren et al. | arXiv | 74 | |
| 2026-10-02 | 2610.02196 | InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation | Zhuo Lin et al. | arXiv | 31 | |
| 2026-09-30 | 2609.33326 | ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces | Jerry Wang et al. | arXiv | 23 | |
| 2026-09-30 | 2609.33591 | Pretraining Transformers with Quantized Softmax in Attention | Shangzhen Zhu et al. | arXiv | 6 | |
| 2026-09-29 | 2609.33586 | Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration | Shangzhen Zhu et al. | arXiv | 4 | |
| 2026-09-29 | 2609.36219 | LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning | Bang Xiao et al. | arXiv | 2 | |
| 2026-09-14 | 2609.12101 | Competence-Gated Pooling of Language Models and Priors for Event Forecasting | Aditi Tiwari et al. | arXiv | 2 | |
| 2026-09-14 | 2609.12078 | Feature Recovery for Object Understanding After Irreversible Fire Damage | Aditi Tiwari et al. | arXiv | 1 | |
| 2026-09-10 | 2608.12564 | Scaling Automatic Research Agents via World Models | Xiyuan Yang et al. | arXiv | 82 | |
| 2026-09-01 | 2608.28833 | Evaluating the Hidden Costs of Personalization in Large Language Models | Yumeng Wang et al. | arXiv | 30 | |
| 2026-08-27 | 2608.19583 | VGI-Bench: Probing Visual Intelligence in Video Generation Models | Xuan He et al. | arXiv | 57 | |
| 2026-08-24 | 2608.21278 | CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment | Chengxiao Wang et al. | arXiv | 6 | |
| 2026-08-14 | 2608.06867 | LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers | Tao Feng et al. | arXiv | 49 | |
| 2026-08-13 | 2608.12307 | AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses | Cheng Qian et al. | arXiv | 107 | |
| 2026-08-10 | 2607.26178 | DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues | Takyoung Kim et al. | arXiv | 11 | |
| 2026-07-31 | 2607.27372 | Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation | Alexi Gladstone et al. | arXiv | 17 | |
| 2026-07-22 | 2607.18754 | AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents | Kunlun Zhu et al. | arXiv | 24 | |
| 2026-07-20 | 2607.10966 | SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning | Mingyuan Wu et al. | arXiv | 4 | |
| 2026-07-07 | 2607.00597 | Multi-Turn Agentic Scientific Literature Search via Workflow Induction | Jisen Li et al. | arXiv | 23 | |
| 2026-06-30 | 2606.24256 | Trimming the Long-Tail of Visual World Modeling Evaluation | Bingxuan Li et al. | arXiv | 31 | |
| 2026-06-29 | 2606.28187 | GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems | Xiaocheng Yang et al. | arXiv | 13 | |
| 2026-06-23 | 2606.22388 | PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems | Jiayu Liu et al. | arXiv | 92 | |
| 2026-06-17 | 2606.15134 | Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings | Shubhang Bhatnagar et al. | arXiv | 2 | |
| 2026-06-16 | 2606.15956 | You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences | Ninad Daithankar et al. | arXiv | 12 | |
| 2026-06-11 | 2606.11482 | Building Social World Models with Large Language Models | Haofei Yu et al. | arXiv | 4 | |
| 2026-06-10 | 2606.10061 | BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts | Kazi Noshin et al. | arXiv | 1 | |
| 2026-06-05 | 2606.05622 | AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints | Jiayu Liu et al. | arXiv | 44 | |
| 2026-05-29 | 2605.26029 | CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists | Junlin Yang et al. | arXiv | 13 | |
| 2026-05-28 | 2605.26396 | Advancing Creative Physical Intelligence in Large Multimodal Models | Cheng Qian et al. | arXiv | 19 | |
| 2026-05-22 | 2605.22642 | Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning | Banghao Chi et al. | arXiv | 35 | |
| 2026-05-20 | 2605.15514 | RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably | Yufeng Du et al. | arXiv | | |
| 2026-05-19 | 2605.15764 | GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions | Junho Kim et al. | arXiv | 3 | |
| 2026-05-15 | 2605.00180 | RouteProfile: Elucidating the Design Space of LLM Profiles for Routing | Jingjun Xu et al. | arXiv | 29 | |
| 2026-05-15 | 2605.15012 | Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance | Kai Yan et al. | arXiv | 2 | |
| 2026-05-14 | 2605.12975 | Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation | Jiashuo Sun et al. | arXiv | 8 | |
| 2026-05-13 | 2605.12978 | Useful Memories Become Faulty When Continuously Updated by LLMs | Dylan Zhang et al. | arXiv | 18 | |
| 2026-05-13 | 2605.11182 | The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes | Siqi Zhu et al. | arXiv | 4 | |
| 2026-05-11 | 2605.05558 | Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages | Siqi Zhu | arXiv | 1 | |
| 2026-05-07 | 2605.02910 | CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing | Cheng Qian et al. | arXiv | 22 | |
| 2026-05-05 | 2605.01214 | Agentic AI Systems Should Be Designed as Marginal Token Allocators | Siqi Zhu | arXiv | 2 | |
| 2026-05-01 | 2604.27351 | Heterogeneous Scientific Foundation Model Collaboration | Zihao Li et al. | arXiv | 127 | |