Key papers

• Group Sequence Policy Optimization (2025)
  Chujie Zheng et al.
  24.20
• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (2025)
  Yang Yue et al.
  16.45
• We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning (2025)
  Runqi Qiao and Qiuna Tan and Peiqing Yang and Yanzi Wang and Xiaowan Wang and Enhui Wan and Sitong Zhou and Guanting Dong and Yuchen Zeng and Yida Xu and Jie Wang and Chong Sun and Chen Li and Honggang Zhang
  16.20
• SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild (2025)
  Weihao Zeng et al.
  15.29
• Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning (2019)
  Alper Kamil Bozkurt et al.
  14.93
• R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization (2025)
  Jingyi Zhang et al.
  14.05
• ToolRL: Reward is All Tool Learning Needs (2025)
  Cheng Qian et al.
  13.76
• GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning (2025)
  GLM-V Team: Wenyi Hong et al.
  13.62
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning (2025)
  Huatong Song et al.
  13.61
• Bayesian policy gradient and actor-critic algorithms (2026)
  Mohammad Ghavamzadeh et al.
  13.41
• On-line Policy Improvement using Monte-Carlo Search (2025)
  Gerald Tesauro et al.
  13.36
• R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model (2025)
  Hengguang Zhou and Xirui Li and Ruochen Wang and Minhao Cheng and Tianyi Zhou and Cho-Jui Hsieh
  12.65
• You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories (2026)
  Zhepei Wei et al.
  12.51
• Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning (2026)
  Renjie Mao et al.
  12.37
• InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners (2025)
  Yuhang Liu et al.
  12.10
• RL's Razor: Why Online Reinforcement Learning Forgets Less (2025)
  Idan Shenfeld et al.
  12.05
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models (2026)
  Bowen Ping et al.
  12.03
• Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning (2025)
  Sikuan Yan et al.
  11.97
• Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models (2025)
  Zhipeng Chen et al.
  11.95
• Reinforcement Learning in POMDP's via Direct Gradient Ascent (2025)
  Jonathan Baxter and Peter L. Bartlett
  11.95
• Agentic Reinforced Policy Optimization (2025)
  Guanting Dong et al.
  11.82
• ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking (2026)
  Qiang Zhang et al.
  11.79
• R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning (2025)
  Jiaxing Zhao et al.
  11.76
• Maximum Entropy Semi-Supervised Inverse Reinforcement Learning (2026)
  Julien Audiffren et al.
  11.75
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning (2025)
  Haozhan Li et al.
  11.65
• RLPR: Extrapolating RLVR to General Domains without Verifiers (2025)
  Tianyu Yu et al.
  11.06
• Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning (2025)
  Yixuan Even Xu et al.
  11.02
• Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling (2026)
  Yucheng Li et al.
  10.98
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents (2026)
  Bowen Wang et al.
  10.82
• Flow Matching Policy Gradients (2025)
  David McAllister et al.
  10.56
• Optimizing Visual Generative Models via Distribution-wise Rewards (2026)
  Ruihang Li et al.
  10.21
• DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO (2025)
  Jinyoung Park et al.
  9.94
• Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning (2025)
  Haozhen Zhang et al.
  9.89
• Energy-Weighted Flow Matching for Offline Reinforcement Learning (2025)
  Shiyuan Zhang and Weitong Zhang and Quanquan Gu
  9.88
• Tree Search for LLM Agent Reinforcement Learning (2025)
  Yuxiang Ji et al.
  9.57
• RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning (2025)
  Kun Lei et al.
  9.41
• Application of Deep Reinforcement Learning to UAV Swarming for Ground Surveillance (2025)
  Ra\'ul Arranz et al.
  9.38
• BuildingGym: An open-source toolbox for AI-based building energy management using reinforcement learning (2025)
  Xilei Dai et al.
  9.35
• Multi-Agent Evolve: LLM Self-Improve through Co-evolution (2025)
  Yixing Chen et al.
  9.26
• OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration (2026)
  Xinchen Zhang et al.
  9.22
• ISO: An RLVR-Native Optimization Stack (2026)
  Hanqing Zhu et al.
  9.11
• Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning (2026)
  Jian Hu et al.
  9.11
• Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models (2025)
  Man Fai Wong et al.
  9.09
• Scaling RL to Long Videos (2025)
  Yukang Chen et al.
  9.07
• CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models (2025)
  Runpeng Dai et al.
  9.04
• Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning (2026)
  Jean-Bastien Grill et al.
  8.99
• StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason (2025)
  Kaiyi Zhang et al.
  8.92
• Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL (2025)
  Che Liu et al.
  8.90
• QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation (2025)
  Jiazheng Li et al.
  8.84
• ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation (2026)
  Hongru Hou et al.
  8.74
• Target Policy Optimization (2026)
  Jean Kaddour
  8.67
• A reinforcement learning agent for maintenance of deteriorating systems with increasingly imperfect repairs (2025)
  Alberto Pliego Marug\'an et al.
  8.64
• ReCode: Reinforcing Code Generation with Reasoning-Process Rewards (2025)
  Lishui Fan et al.
  8.61
• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning (2025)
  Shu Zhao et al.
  8.61
• Pareto Set Learning for Multi-Objective Reinforcement Learning (2025)
  Erlong Liu et al.
  8.59
• Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning (2025)
  Syeda Nahida Akter et al.
  8.58
• 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities (2025)
  Kevin Wang et al.
  8.52
• Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning (2025)
  Alexander Golubev et al.
  8.51
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model (2025)
  Ling Team et al.
  8.51
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning (2026)
  Heming Zou et al.
  8.51