Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Momentum

144 papers in the last four weeks, up 243% on the four weeks before. 1.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,138

All topics

Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation
May 1, 2026Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang +3RL for Code Generation Reinforcement Learning
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China · School of Artificial Intelligence, Nanjing University, Nanjing 210023, China
Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization
May 1, 2026Yue Mao, Shicheng Liu, Siyuan Xu +1Reinforcement Learning
Department of Mechanical Engineering, Pennsylvania State University · Department of Electrical Engineering, Pennsylvania State University
Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation
May 1, 2026Haichen Hu, Jian Qian, David Simchi-LeviRegret Minimization in RL Markov Decision Processes
Laboratory for Information and Decision Systems · Department of AI and Data Science
Interpretable experiential learning based on state history and global feedback
May 1, 2026Anton KoloninReinforcement Learning Game-Playing Agents
1The Artificial Intelligence Research Center, Novosibirsk State University, Russia · 2Aigents, Russia.
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
May 1, 2026Zihan Lin, Xiaohan Wang, Jie Cao +6RL for Language Models Reinforcement Learning
MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China · Meituan, Beijing, China · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China.
Data Deletion Can Help in Adaptive RL
Apr 30, 2026Param Budhraja, Aditya Gangrade, Alex Olshevsky +1Non-Stationary RL Reinforcement Learning
Department of Electrical and Computer Engineering, Boston University, Boston, MA 02215, USA · Faculty of Electrical and Computer Engineering, Systems Engineering, Boston University, Boston, MA 02215, USA
Pessimism-Free Offline Learning in General-Sum Games via KL Regularization
Apr 30, 2026Claire Chen, Yuheng ZhangNash Equilibrium Reinforcement Learning
The Division of Physics, Mathematics and Astronomy California Institute of Technology · Department of Computer Science University of Illinois Urbana-Champaign
Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback
Apr 30, 2026Yikai Wang, Shang Liu, Jose BlanchetRegret Minimization in RL Reinforcement Learning
Department of Statistics and Operations Research, University of North Carolina · Imperial Business School, Imperial College London · Department of Management Science and Engineering, Stanford University
RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses
Apr 30, 2026Feiyu Wu, Xu Zheng, Zhuocheng Wang +2Reinforcement Learning LLM-Guided RL
School of Cyber Engineering, Xidian University
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Apr 30, 2026Jingcheng Deng, Zihao Wei, Liang Pang +4Reinforcement Learning RL for Language Model Reasoning
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
Apr 30, 2026Junan Hu, Jian Liu, Jingxiang Lai +6Reinforcement Learning RL for GUI Agents
1Shandong University · 2The Hong Kong University of Science and Technology · 3The Hong Kong University +2
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Apr 30, 2026Hanzhong Guo, Jie Wu, Jie Liu +6Reward Modeling Reinforcement Learning
School of Computing and Data Science, The University of Hong Kong · ByteDance Seed · CUHK +1
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
Apr 30, 2026Yang Zhang, Jiangyuan Zhao, Chenyou Fan +11Reinforcement Learning Long-Horizon Robotic Manipulation
Institute of Artificial Intelligence (TeleAI), China Telecom · Tsinghua University · Shanghai Jiao Tong University +1
Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms
Apr 30, 2026Zhenjie Ren, Xiaoli Wei, Xiang Yu +1Reinforcement Learning Stochastic Optimal Control
LaMME, Universit´e ´Evry Paris-Saclay, ´Evry, France · Department of Applied Mathematics, The Hong Kong Polytechnic University, Kowloon, Hong Kong · Department of Industrial Engineering and Operations Research, Columbia University, New York, USA
Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction
Apr 30, 2026Wentao Chen, Jingtang Chen, Mingjian Fu +4Reinforcement Learning UAV Navigation
AutoREC: A reinforcement learning platform for equivalent circuit model generation
Apr 29, 2026Ali Jaberi, Yonatan Kurniawan, Robert Black +5Reinforcement Learning System Identification
Clean Energy Innovation Research Centre, National Research Council Canada, Mississauga, ON, Canada · Department of Materials Science and Engineering, University of Toronto, Toronto, ON, Canada · Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada +1
Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training
Apr 29, 2026Mahya Ramezani, Holger VoosReinforcement Learning UAV Navigation
Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg.
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Apr 29, 2026Hayate Iso, Tiyasa Mitra, Sudipta Mondal +15Reinforcement Learning Speculative Decoding
NVIDIA
FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
Apr 29, 2026Zhixin Han, Yanzhi Zhang, Chuyang Wei +11Agentic RL Reinforcement Learning
College of Software, Nankai University · Zhongguancun Academy, Beijing, China · Academy of Mathematics and Systems Science, Chinese Academy of Sciences +3
Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning
Apr 29, 2026Seungyub Han, Hyungjin Kim, Jungwoo LeeReinforcement Learning Offline RL
Seoul National University
Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
Apr 29, 2026Disha SinghaReward Hacking Reinforcement Learning
Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control
Apr 29, 2026Bolian Li, Yifan Wang, Yi Ding +3RL for Language Models Reinforcement Learning
Purdue University, West Lafayette, IN, USA
DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
Apr 29, 2026Tianhao Hu, Xiangcheng Liu, Youshao Xiao +15RL for Language Models Asynchronous RL
Meituan, China
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
Apr 28, 2026Chu-Cheng Lin, Eugene IeSupervised Fine-Tuning Reinforcement Learning
Google
Sample-efficient Neuro-symbolic Proximal Policy Optimization
Apr 28, 2026Simone Murari, Celeste Veronese, Daniele MeliReinforcement Learning Proximal Policy Optimization
Dept. of Computer Science, University of Verona, Italy
Improving Zero-Shot Offline RL via Behavioral Task Sampling
Apr 28, 2026Nazim Bendib, Nicolas Perrin-Gilbert, Olivier SigaudReinforcement Learning Offline RL
Institut des Systèmes Intelligents et de Robotique, ISIR, Sorbonne Université, Paris, France.
DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
Apr 28, 2026Hanqing Yang, Qiang Zhou, Yongchao Du +6Reinforcement Learning Text-Guided Image Editing
Alibaba Group · Zhejiang University
Safe-Support Q-Learning: Learning without Unsafe Exploration
Apr 28, 2026Yeeun Lim, Narim Jeong, Donghwan LeeReinforcement Learning KL-Regularized RL
HD Korea Shipbuilding & Offshore Engineering · Department of Electrical Engineering, KAIST, Daejeon, South Korea
How Can Reinforcement Learning Achieve Expert-level Placement?
Apr 28, 2026Ruo-Tong Chen, Ke Xue, Chengrui Gao +7Reinforcement Learning Electronic Design Automation
State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · Huawei Noah’s Ark Lab, China
Model-Aware Data Cleaning for Tabular Foundation Models
Apr 28, 2026Laure Berti-EquilleTabular Foundation Models Reinforcement Learning
IRD, ESPACE-DEV Montpellier, France

May 1, 2026, cs.LGJ/K move · Enter open · S save

Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation

Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang, Hui Sun+2

State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China · School of Artificial Intelligence, Nanjing University, Nanjing 210023, China

RL for Code Generation Reinforcement Learning Critic-Free RL Reinforcement Learning with Verifiable Rewards Reward Design for RL

Open paper AskPDF arXiv

Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward. In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments. To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pass solutions. This arises because test-case pass rate is a miscalibrated surrogate for progress toward full correctness, and partial-pass solutions within the same group can induce conflicting gradient directions that cancel out. Overall, our results suggest that, in critic-free RL, pass-rate rewards are insufficient to improve code generation and motivate reward designs that better align optimization with the goal of full correctness.

Momentum

Related topics

Latest papers 1,138