| 1 | world2vec: Mechanistic world models through latent dynamics learning | Tobias Schmidt, Rodrigo Gonzalez Laiz, Krisztián Szuppinger +1 | cs.LG | 2026-10-29 |
| 2 | ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender | Qiyao Ma, Xiaodong Liu, Weiwei Yang +9 | cs.CL | 2026-10-29 |
| 3 | PIVOT: Progressive Intervention via Online Teacher Correction | Zhihao Yang, Boyuan Zheng, Puhui Tan +7 | cs.CL | 2026-10-29 |
| #4 | Gym-Anything for Robotics: Scaling physical simulations with digital agents | Pranjal Aggarwal, Sean Welleck | cs.RO | 2026-10-29 |
| #5 | Training language models in simulation for psychiatric intake | Samuel Schmidgall, Tim Strother, Alex Bijamov +53 | cs.AI | 2026-10-29 |
| #6 | SCARL: Sequence Confidence-Aligned Reinforcement Learning | Zhenghong Ke, Jingbo Zhou, Hua Wu | cs.LG | 2026-10-29 |
| #7 | Composing and Steering Diffusion Models with Generalized Feynman-Kac Correctors | Wael Mattar, Daniel Freedman | cs.LG | 2026-10-29 |
| #8 | Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR | Lang Chen, Zongxin Xu, Borui Wang +2 | cs.AI | 2026-10-29 |
| #9 | EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation | Ankush Kadu, Athira Gopal, Niharika Singh +2 | cs.AI | 2026-10-29 |
| #10 | EpiAgent: Epistemic Self-Play for LLM Agents | Xuanfa Jin, Xinyu Cui, Zhijian Ma +4 | cs.AI | 2026-10-29 |
| #11 | DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning | Md. Rakibul Hassan, Majedul Islam, Md. Ashraful Alam +2 | cs.CR | 2026-10-29 |
| #12 | Reward-Adaptive Co-Evolution of Policy and Rubric | Yizhu Chen, Jianguang Jiang, Jiameng Huang +5 | cs.AI | 2026-10-29 |
| #13 | H$^2$R: Hierarchical Hint-Based Reward for Mathematical Reasoning via Reinforcement Learning | He Tu, Siye Li, Hongyi Wen | cs.LG | 2026-10-29 |
| #14 | Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding | Hongyu Bai, Jiaqi Zeng, Chunzheng Zhu | cs.CV | 2026-10-29 |
| #15 | Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels | Qin-Wen Luo, Sheng Ren, Xiang Chen +6 | cs.LG | 2026-10-29 |
| #16 | Incentivizing Self-Learning in Large Language Models via Reinforcement Learning | Lingkai Kong, Yuzhe Gu, Haiteng Zhao +6 | cs.CL | 2026-10-29 |
| #17 | EditAgent: Rethinking Agentic Image Editing | Haiyang Xu, Tianyu Wang, Jialu Li +5 | cs.CV | 2026-10-29 |
| #18 | Look at Where You Think: Localization-Head Alignment for Fine-Grained Perception in Thinking VLMs | Yuan Wang, Wei Wu, Hongning Wang | cs.CV | 2026-10-29 |
| #19 | DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems | Ni Zhang, Zhiqin Zhang, Ling Pan +2 | cs.AI | 2026-10-29 |
| #20 | Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning | Haotian Lyu, Haoyu Wang, Ru Wang +4 | cs.AI | 2026-10-29 |
| #21 | Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence | Chenxi Li, Yao Shu, Siyang Gao +2 | cs.LG | 2026-10-29 |
| #22 | Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models | Chengwei Zhou, Zhaoyan Jia, Massoud Pedram +1 | cs.CL | 2026-10-29 |
| #23 | Before the Next Rollout: Diagnosing Skill Utility Shifts from Policy Updates | Yifan Wang, Zhenyi Gai, Yiwen Zhao +5 | cs.AI | 2026-10-29 |
| #24 | RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories | Tidor-Vlad Pricope | cs.LG | 2026-10-29 |
| #25 | MRC-MMAgent: Reinforcement Learning for Multi-Role Collaboration in Multimodal Tool-Using Agents | Shengqin Wang, Jie Jin, Xiaofan Li +8 | cs.CV | 2026-10-29 |
| #26 | Satisficing Regret Minimization in Bandits with Knapsacks | Qing Feng, Tianyi Ma, Ruihao Zhu | stat.ML | 2026-10-29 |
| #27 | There Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price | Yinuo Liu | cs.LG | 2026-10-29 |
| #28 | DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition | Zhiqiang Wu, Shuang Sun, Jiale Zhang +4 | cs.CV | 2026-10-29 |
| #29 | Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps | Peitong Duan, Khashayar Gatmiry, Jeffrey Nichols +2 | cs.AI | 2026-10-29 |
| #30 | Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents | Yuxiang Chai, Quyu Kong, Panrong Tong +2 | cs.AI | 2026-10-29 |
| #31 | Grounding Multimodal Reasoning with Evidence-Ablated Negatives | Chenxi Liu, Tianyi Xiong, Yanshuo Chen +1 | cs.CL | 2026-10-29 |
| #32 | Event2Reward: Learning Robotic Rewards from Progress Relations | Junnan Nie, Zitian Fan, Jiachen Zhang +14 | cs.RO | 2026-10-29 |
| #33 | Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models | Aishik Nagar, Cheston Tan | cs.AI | 2026-10-29 |
| #34 | When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown | Yuv Raj Pant, Moshiur Rahman Tonmoy, Kaiqun Fu | cs.LG | 2026-10-28 |
| #35 | Reinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach | Ajay Vikram Periasami, Anjaneya Gupta, Ethan Cheng +1 | cs.LG | 2026-10-28 |
| #36 | Rethinking GFlowNet Training: Negative Reinforce Dynamics | Pedro Dall'Antonia, Daniel Csillag, Diego Mesquita | cs.LG | 2026-10-28 |
| #37 | Planned Restlessness: Delayed Meta Bandits with Budgets | Sudipto Guha | cs.LG | 2026-10-28 |
| #38 | MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems | Hehai Lin, Qi Yang, Chengwei Qin | cs.MA | 2026-10-28 |
| #39 | Aligning Autoresearch: Co-Improvement between Agents and Humans | Tianjian Li, Chuanyang Jin, Seungone Kim +10 | cs.AI | 2026-10-28 |
| #40 | Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training | Albert Bou, Javier Valdes-Aleman, Jon M. Laurent +4 | cs.AI | 2026-10-28 |
| #41 | Discovery of Diverse and Realistic Financial Tail-Risk Using Generative Flow Networks | Adir Serruya, Gilad Katz | cs.LG | 2026-10-28 |
| #42 | Discovering Jailbreaks via Curriculum of Models | Michał Burzyński, Noah T. Rossi, Shomit Basu +1 | cs.LG | 2026-10-28 |
| #43 | Routed Continual Learning | Michael Philip, Mahesh Balakrishnan, David Geraghty +3 | cs.LG | 2026-10-28 |
| #44 | Latent Decision Flow Rewards for Clinical Guideline Reasoning | Gaurav Bhatt, Marinka Zitnik | cs.LG | 2026-10-28 |
| #45 | Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation | Jacob Levy, Arthur Bouton, Tristan D. Hassler +2 | cs.RO | 2026-10-28 |
| #46 | On-Policy Self-Distillation with Teacher Evolution | Shufan Shen, Zhongni Hou, Chao Bi +3 | cs.LG | 2026-10-28 |
| #47 | Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty | Atin Chowdhury, Piyush Joshi | cs.AI | 2026-10-28 |
| #48 | Repairs for Whom? Evaluator-Executor Mismatch in Selecting Repairs for Failed LLM Agents | Yijun Liao, Fanwei Liang | cs.SE | 2026-10-28 |
| #49 | A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement | Yu Liu, Youxing Li, Yuedong Tan +17 | cs.AI | 2026-10-28 |
| #50 | Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation | Chengsheng Zhang, Wenshen Xu, Yuchuan Wu +6 | cs.AI | 2026-10-28 |