Large Language Model Reinforcement Learning

Ask about this topic

Momentum

17 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 194

All topics
CardsList

  1. Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning

    Jul 5, 2026Faid Keddouri, Sohaib Houhou, Aissa Boulmerka +1Potential-Based Reward ShapingMulti-Agent Reinforcement Learning

    National School of Artificial Intelligence (ENSIA), Sidi Abdellah Campus, Algiers, Algeria · Cosys-Grettia, Univ Gustave Eiffel, F-77454 Marne-la-Vallee, France.

  2. On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models

    Jul 5, 2026Chee Heng Tan, Zhuoyi Lin, Mehul Motani +1Large Language Model Reinforcement LearningLarge Language Model Reliability

    School of Computing National University of Singapore · Institute of Advanced Intelligence and Computing Agency for Science, Technology and Research · Department of Electrical & Computer Engineering National University of Singapore

  3. Aligning Language Models with Selective Prediction

    Jul 3, 2026Gaoxiang Luo, Yifan Wu, Sinian Zhang +2Large Language Model AlignmentLarge Language Model Reliability

    Department of Computer Science and Engineering · 2Bioinformatics and Computational Biology Program · 3Division of Biostatistics and Health Data Science

  4. Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

    Jul 3, 2026Jiyang Guan, Yong Xie, Jun Chen +6Safety AlignmentLarge Language Model Alignment

    Alibaba AAIG

  5. Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling

    Jul 2, 2026Xuqing Yang, Yi Yuan, Shanzhe Lei +1Confidence EstimationLarge Language Model Reliability

    Shanghai Jiao Tong University · Southeast University · Shanghai AI Laboratory

  6. SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing

    Jun 30, 2026Ruikang Zhao, Zhenting Wang, Han Gao +1Diffusion Language ModelsLarge Language Model Reinforcement Learning

    Technical University of Denmark · MBZUAI Institute of Foundation Models · Iowa State University +1

  7. Addressing Over-Refusal in LLMs with Competing Rewards

    Jun 30, 2026Taeyoun Kim, Aviral KumarLarge Language Model SafetyLLM Reasoning Strategies

    Carnegie Mellon University · SynthLabs

  8. DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

    Jun 29, 2026Haisen Luo, Yiwei Liu, Haoning Wang +13Unsupervised On-Policy Self-DistillationLarge Language Model Reinforcement Learning

    3Beike Language and Intelligence · 2ENS Paris-Saclay · 1Tsinghua University

  9. ARKD: Adaptive Reinforcement Learning-Guided Bidirectional KL Divergence Distillation for Text Generation

    Jun 29, 2026Zilong Liu, Xuewen Zhang, Jinrui Xing +3Probe-Logit DistillationKullback-Leibler Divergence

    Li Auto, Beijing, China · School of Software and Microelectronics, Peking University, China

  10. The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

    Jun 28, 2026Jing Liang, Hongyao Tang, Yi Ma +9Large Language Model Reinforcement LearningTraining-Inference Mismatch

    1Tianjin · 2Alibaba

  11. RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning

    Jun 25, 2026Rongjian Chen, Jianmin Hu, Kejiang Ye +1Large Language Model Reinforcement LearningRollout

    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · University of Chinese Academy of Sciences, Beijing, China · Southern University of Science and Technology, Shenzhen, China

  12. GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning

    Jun 25, 2026Ting Zhou, Zhenqing Ling, Yiyang Zhao +2Large Language Model AlignmentLarge Language Model Reinforcement Learning

    Sun Yat-Sen University, Guangzhou, China · Alibaba Group, Hangzhou, China · Guangdong Tobacco Guangzhou Co., Ltd., Guangzhou, China

  13. Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

    Jun 24, 2026Yupu Hao, Zhuoran Jin, Huanxuan Liao +2Large Language Model Reinforcement LearningAgentic Reinforcement Learning

    1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

  14. OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning

    Jun 24, 2026Wenxuan Jiang, Zining Fan, Zijian Zhang +6LLM Reasoning StrategiesLarge Language Model Reinforcement Learning

    The Hong Kong Polytechnic University · Peking University · Meituan Longcat Team +2

  15. Learning with a Single Rollout via Monte Carlo Pass@k Critic

    Jun 24, 2026Fengdi Che, Yang Liu, Lei Yu +4Large Language Model Reinforcement LearningCredit Assignment

    University of Alberta · BIGAI · University of Toronto +4

  16. EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning

    Jun 22, 2026Hongxin Ding, Baixiang Huang, Yue Fang +6On-Policy Self-EvolutionLarge Language Model Reinforcement Learning

    National Engineering Research Center of Software Engineering, Peking University, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education +2

  17. Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model

    Jun 21, 2026Pengxiang Cai, Tianchen Fang, Xiaohan Li +3Curriculum Reinforcement LearningLarge Language Model Reinforcement Learning

    The Hong Kong University of Science and Technology (Guangzhou) · Nanyang Technological University · Zhejiang University

  18. Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning

    Jun 21, 2026Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang +7Large Language Model Reinforcement LearningLarge Language Model Training

    Johns Hopkins University · Rice University · University of Haifa +2

  19. Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

    Jun 20, 2026Zhao Yang, Yuxuan Jiang, Ting-Chih Chen +18Large Language Model Reinforcement LearningOffline Reinforcement Learning

    VU Amsterdam, The Netherlands · University of Maryland, Baltimore County, USA · Leiden University, The Netherlands +4

  20. Depth-Entropy Guided Sampling for Training-Free LLM Reasoning

    Jun 19, 2026Zibin Meng, Peng Xie, Kani ChenLLM Reasoning StrategiesRecursive Reasoner

    1The Hong Kong University of Science and Technology

  21. Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models

    Jun 18, 2026Darrien McKenzie, Nicklas Hansen, Xiaolong WangCurriculum Reinforcement LearningLarge Language Model Reinforcement Learning

    University of California, San Diego

  22. Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

    Jun 17, 2026Xiaoyue Xu, Sikui Zhang, Xiaorong Wang +2Large Language Model Reinforcement LearningLong-Context Reasoning

    OpenBMB · Tsinghua University

  23. From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

    Jun 16, 2026Lingjing Kong, Xin Liu, Guangyi Chen +9LLM Reasoning StrategiesCompositional Generalization

    Carnegie Mellon University · Mohamed bin Zayed University of Artificial Intelligence · Institute of Foundation Models +1

  24. Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

    Jun 16, 2026Ziliang Wang, Kang An, Faqiang Qian +5Large Language Model Reinforcement LearningLLM Reasoning Strategies

    1SenseTime · 2Shanghai Jiao Tong University

  25. From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

    Jun 16, 2026Chao Chen, Chengzu Li, Zhiwei Li +2Large Language Model Reinforcement Learning

    1LARK, HKUST (GZ) · University of Cambridge · 3HKUST

  26. The Value Axis: Language Models Encode Whether They're on the Right Track

    Jun 15, 2026Nick Jiang, Isaac Kauvar, Jack LindseyLarge Language Model Reinforcement LearningValue

    1Stanford University · 2Anthropic

  27. ExpRL: Exploratory RL for LLM Mid-Training

    Jun 15, 2026Violet Xiang, Amrith Setlur, Chase Blagden +2Large Language Model Reinforcement LearningLLM Reasoning Strategies

    1Stanford University · 2Carnegie Mellon University · 3OpenAI +1

  28. OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing

    Jun 14, 2026Zebang Cheng, Shuimu Chen, Boxue Yang +7Unsupervised On-Policy Self-DistillationLarge Language Model Reinforcement Learning

    Shenzhen University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Tsinghua University +6

  29. Reinforcement Learning for LLM-based Event Forecasting

    Jun 14, 2026Amit Arnold LevyLarge Language Model Reinforcement LearningData-Driven Forecasting

    University of Oxford

  30. Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning

    Jun 13, 2026Zirui Pang, Chenlong Zhang, Haosheng Tan +3Large Language Model UnlearningLarge Language Model Reinforcement Learning

    The Hong Kong University of Science and Technology (Guangzhou) · Institute of Automation, Chinese Academy of Sciences · University of Glasgow

  31. ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

    Jun 11, 2026Xucong Wang, Ziyu Ma, Yong Wang +5Large Language Model Reinforcement LearningLLM Reasoning Strategies

    University of Science and Technology of China · 2AMAP, Alibaba Group

  32. Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

    Jun 10, 2026Yucheng Li, Huiqiang Jiang, Yang Xu +14Large Language Model Reinforcement LearningOffline Reinforcement Learning

    Qwen Team, Alibaba Inc.

  33. ReCal: Reward Calibration for RL-based LLM Routing

    Jun 10, 2026Qihang Yu, Hanwen Tong, Zhengqi Zhang +5Large Language Model RoutingLarge Language Model Reinforcement Learning

    Zhejiang University · Ant Group · Shanghai AI Laboratory

  34. Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning

    Jun 10, 2026Kai Liu, Peijie Dong, Xinchen Xie +5Mathematical Reasoning BenchmarksLarge Language Model Reinforcement Learning

    Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University · Hong Kong University of Science and Technology (Guangzhou) · Shanghai AI Laboratory

  35. How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

    Jun 9, 2026Zhichen Dong, Yang Li, Yuhan Sun +9Large Language Model Reinforcement LearningLLM Reasoning Strategies

    1Shanghai Jiao Tong University · 2Alibaba Group · 3Shanghai Artificial Intelligence Laboratory

  36. Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning

    Jun 9, 2026Jiangnan Xia, Yucheng Shi, Yu Yang +3Large Language Model Reinforcement LearningMemorization

    University of Georgia · Tencent AI Lab · The Education University of Hong Kong +1

  37. Rethinking the Divergence Regularization in LLM RL

    Jun 8, 2026Jiarui Yao, Xiangxin Zhou, Penghui Qi +3Large Language Model Reinforcement LearningTrust Region

    1Tencent Hunyuan · 2UIUC · 3NUS

  38. Gradient-Guided Reward Optimization for Inference-time Alignment

    Jun 8, 2026Hankun Lin, Ruqi ZhangLarge Language Model AlignmentReward Gradients

    Department of Computer Science, Purdue University

  39. 3SPO: State-Score-Supervised Policy Optimization for LLM Agents

    Jun 8, 2026Yu Han, Kailing Li, Yang Jiao +4Large Language Model Reinforcement LearningOffline Reinforcement Learning

    School of Computer Science and Technology, East China Normal University · Fudan University · KAUST +1

  40. Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy

    Jun 7, 2026Jiashun Liu, Runze Liu, Xu Wan +3Large Language Model Reinforcement LearningTraining-Inference Mismatch

    1Hong Kong University of Science and Technology · 2Zhejiang University · 3Tianjin University

  41. Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models

    Jun 7, 2026Yawen Shao, Jie Xiao, Kai Zhu +6Large Language Model Reinforcement LearningDiffusion Language Models

    University of Science and Technology of China · Tongyi Lab · Northeastern University

  42. GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning

    Jun 7, 2026Yanyan Wu, Boyi Zhang, Yanlin Liu +10Large Language Model Reinforcement LearningOffline Reinforcement Learning

    East China University of Science and Technology · University of Science and Technology of China · Southwestern University of Finance and Economics +5

  43. Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models

    Jun 7, 2026Yang Zhou, Ranajoy Sadhukhan, Zhaofeng Sun +7Autoregressive RolloutLarge Language Model Reinforcement Learning

    Carnegie Mellon University · Cornell University · Intel +1

  44. Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation

    Jun 6, 2026Boxuan Lyu, Haiyue Song, Zhi Qu +3Machine Translation QualityMachine Translation

    Institute of Science Tokyo · Preferred Networks, Inc. · Nara Institute of Science and Technology

  45. SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models

    Jun 5, 2026Yuchen He, Baolong Bi, Shenghua Liu +7Multi-Objective Reinforcement LearningLarge Language Model Reinforcement Learning

    Institute of Computing Technology, Chinese Academy of Sciences · University of Electronic Science and Technology of China

  46. Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models

    Jun 3, 2026Anant Khandelwal, Manish GuptaLarge Language Model Reinforcement LearningDiffusion Language Models

    Microsoft AI, India

  47. Efficient Hyperparameter Optimization for LLM Reinforcement Learning

    Jun 2, 2026Minping Chen, Bowen Xiao, Du Liang +2Large Language Model Reinforcement LearningGeneral Grid Search Framework

    1The Hong Kong University of Science and Technology (Guangzhou) · 3China United Network Communications Group · 2The Hong Kong University of Science and Technology

  48. Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning

    May 30, 2026Xuewei Yang, Jiachen Yu, Jie Wu +3Unsupervised On-Policy Self-DistillationLarge Language Model Reinforcement Learning

    Tsinghua University

  49. PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

    May 29, 2026Daize Dong, Junlin Chen, Haolong Jia +9Large Language Model Reinforcement LearningReplay

    ♣Rutgers University · ♦AMD · ⋆MBZUAI

  50. ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate

    May 29, 2026Rodney Lafuente-MercadoCredit AssignmentLarge Language Model Reinforcement Learning

    Scale AI

  51. Consolidating Rewarded Perturbations for LLM Post-Training

    May 29, 2026Zheyu Zhang, Shuo Yang, Gjergji KasneciLarge Language Model Reinforcement LearningPost-Training

    Technical University of Munich

  52. DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning

    May 29, 2026Yujie Wang, Siwei Chen, Longzan Luo +4Large Language Model Reinforcement LearningAutoregressive Rollout

    School of Computer Science & Beijing Key Laboratory of Software and Hardware Cooperative Artificial Intelligence Systems, Peking University, Beijing, China · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China · Institute of Computational Social Science, Peking University (Qingdao), Qingdao, China

  53. Configurable Reward Model for Balanced Safety Alignment

    May 28, 2026Zhengping Jiang, Mehran Khodabandeh, Akash Bharadwaj +5Safety AlignmentLarge Language Model Alignment

    Johns Hopkins University · Meta · Meta Superintelligence Labs

  54. ESPO: Early-Stopping Proximal Policy Optimization

    May 28, 2026Zihang Li, Rui Zhou, Yingcheng Shi +8Large Language Model Reinforcement LearningProximal Policy Optimization

    1Tongyi Lab , Alibaba Group · 2Peking University

  55. Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning

    May 28, 2026Zizhe Chen, Jiqian Dong, Yizhou Tian +4Large Language Model Reinforcement LearningState Estimation

    Department of Computer Science and Engineering, The Chinese University of Hong Kong · Huawei Technologies Ltd.

  56. The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF

    May 28, 2026Zeli Su, Zhankai Xu, Tianlei Chen +4Large Language Model Reinforcement LearningInstruction-Tuned Models

    Minzu University of China, Beijing, China · Ant Group, Hangzhou, China · Renmin University of China, Beijing, China +1

  57. GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models

    May 28, 2026Xiaohang Tang, Keyue Jiang, Che Liu +4Diffusion Language ModelsLarge Language Model Reinforcement Learning

    UNIST · University of Basel

  58. When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL

    May 27, 2026Youting Wang, Yuan Tang, Bowen Liu +2Large Language Model Reinforcement LearningRefinement

  59. DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

    May 27, 2026Caijun Xu, Changyi Xiao, Zhongyuan Peng +1Large Language Model Reinforcement LearningLarge Reasoning Models

    1Fudan University · 2Shanghai Innovation Institute

  60. Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

    May 26, 2026Yi Jing, Zao Dai, Jinwu Hu +4Large Language Model TrainingLarge Language Model Reinforcement Learning

    Tsinghua University