Awesome Reinforcement Learning

Key papers

• Agenttuning: Enabling Generalized Agent Abilities For Llms (2023)
  Aohan Zeng, Mingdao Liu, Rui Lu, et al.
  32.67
• Step-dpo: Step-wise Preference Optimization For Long-chain Reasoning Of Llms (2024)
  Xin Lai, Zhuotao Tian, Yukang Chen, et al.
  31.31
• Agentverse: Facilitating Multi-agent Collaboration And Exploring Emergent Behaviors (2023)
  Weize Chen, Yusheng Su, Jingwei Zuo, et al.
  29.70
• Helpsteer2: Open-source Dataset For Training Top-performing Reward Models (2024)
  Zhilin Wang, Yi Dong, Olivier Delalleau, et al.
  29.68
• Agentscope: A Flexible Yet Robust Multi-agent Platform (2024)
  Dawei Gao, Zitao Li, Xuchen Pan, et al.
  29.54
• RLAIF Vs. RLHF: Scaling Reinforcement Learning From Human Feedback With AI Feedback (2023)
  Harrison Lee, Samrat Phatale, Hassan Mansoor, et al.
  29.41
• Eureka: Human-level Reward Design Via Coding Large Language Models (2023)
  Yecheng Jason Ma, William Liang, Guanzhi Wang, et al.
  27.82
• Is DPO Superior To PPO For LLM Alignment? A Comprehensive Study (2024)
  Shusheng Xu, Wei Fu, Jiaxuan Gao, et al.
  27.53
• Agentgym: Evolving Large Language Model-based Agents Across Diverse Environments (2024)
  Zhiheng Xi, Yiwen Ding, Wenxiang Chen, et al.
  27.20
• The Unlocking Spell On Base Llms: Rethinking Alignment Via In-context Learning (2023)
  Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, et al.
  26.03
• Direct Nash Optimization: Teaching Language Models To Self-improve With General Preferences (2024)
  Corby Rosset, Ching-An Cheng, Arindam Mitra, et al.
  25.73
• Teaching Large Language Models To Reason With Reinforcement Learning (2024)
  Alex Havrilla, Yuqing Du, Sharath Chandra Raparthy, et al.
  25.08
• Agentohana: Design Unified Data And Training Pipeline For Effective Agent Learning (2024)
  Jianguo Zhang, Tian Lan, Rithesh Murthy, et al.
  24.90
• Self-play With Execution Feedback: Improving Instruction-following Capabilities Of Large Language Models (2024)
  Guanting Dong, Keming Lu, Chengpeng Li, et al.
  24.59
• Personalized Soups: Personalized Large Language Model Alignment Via Post-hoc Parameter Merging (2023)
  Joel Jang, Seungone Kim, Bill Yuchen Lin, et al.
  24.50
• Federatedscope-llm: A Comprehensive Package For Fine-tuning Large Language Models In Federated Learning (2023)
  Weirui Kuang, Bingchen Qian, Zitao Li, et al.
  24.26
• Nash Learning From Human Feedback (2023)
  Rémi Munos, Michal Valko, Daniele Calandriello, et al.
  23.79
• Meta-rewarding Language Models: Self-improving Alignment With Llm-as-a-meta-judge (2024)
  Tianhao Wu, Weizhe Yuan, Olga Golovneva, et al.
  23.63
• Self-exploring Language Models: Active Preference Elicitation For Online Alignment (2024)
  Shenao Zhang, Donghan Yu, Hiteshi Sharma, et al.
  23.63
• Expel: LLM Agents Are Experiential Learners (2023)
  Andrew Zhao, Daniel Huang, Quentin Xu, et al.
  23.10
• Stepcoder: Improve Code Generation With Reinforcement Learning From Compiler Feedback (2024)
  Shihan Dou, Yan Liu, Haoxiang Jia, et al.
  22.83
• Reinforced Self-training (rest) For Language Modeling (2023)
  Caglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan, et al.
  22.75
• LLM Evaluators Recognize And Favor Their Own Generations (2024)
  Arjun Panickssery, Samuel R. Bowman, Shi Feng
  22.26
• Routing To The Expert: Efficient Reward-guided Ensemble Of Large Language Models (2023)
  Keming Lu, Hongyi Yuan, Runji Lin, et al.
  21.60
• Smartplay: A Benchmark For Llms As Intelligent Agents (2023)
  Yue Wu, Xuan Tang, Tom M. Mitchell, et al.
  21.32
• Vineppo: Refining Credit Assignment In RL Training Of Llms (2024)
  Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, et al.
  21.27
• Understanding The Effects Of RLHF On LLM Generalisation And Diversity (2023)
  Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, et al.
  21.24
• Alphazero-like Tree-search Can Guide Large Language Model Decoding And Training (2023)
  Xidong Feng, Ziyu Wan, Muning Wen, et al.
  21.21
• RLEF: Grounding Code Llms In Execution Feedback With Reinforcement Learning (2024)
  Jonas Gehring, Kunhao Zheng, Jade Copet, et al.
  21.18
• Interpretable Preferences Via Multi-objective Reward Modeling And Mixture-of-experts (2024)
  Haoxiang Wang, Wei Xiong, Tengyang Xie, et al.
  20.64
• Recursive Introspection: Teaching Language Model Agents How To Self-improve (2024)
  Yuxiao Qu, Tianjun Zhang, Naman Garg, et al.
  19.75
• RAIN: Your Language Models Can Align Themselves Without Finetuning (2023)
  Yuhui Li, Fangyun Wei, Jinjing Zhao, et al.
  19.73
• LASER: LLM Agent With State-space Exploration For Web Navigation (2023)
  Kaixin Ma, Hongming Zhang, Hongwei Wang, et al.
  19.71
• Optimization-based Prompt Injection Attack To Llm-as-a-judge (2024)
  Jiawen Shi, Zenghui Yuan, Yinuo Liu, et al.
  19.67
• Remax: A Simple, Effective, And Efficient Reinforcement Learning Method For Aligning Large Language Models (2023)
  Ziniu Li, Tian Xu, Yushun Zhang, et al.
  19.63
• Efficient Exploration For Llms (2024)
  Vikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao, et al.
  19.21
• Panacea: Pareto Alignment Via Preference Adaptation For Llms (2024)
  Yifan Zhong, Chengdong Ma, Xiaoyuan Zhang, et al.
  18.85
• Rewarding Progress: Scaling Automated Process Verifiers For LLM Reasoning (2024)
  Amrith Setlur, Chirag Nagpal, Adam Fisch, et al.
  18.76
• Preference Fine-tuning Of Llms Should Leverage Suboptimal, On-policy Data (2024)
  Fahim Tajwar, Anikait Singh, Archit Sharma, et al.
  18.58
• Navgpt-2: Unleashing Navigational Reasoning Capability For Large Vision-language Models (2024)
  Gengze Zhou, Yicong Hong, Zun Wang, et al.
  18.43
• Regularizing Hidden States Enables Learning Generalizable Reward Model For Llms (2024)
  Rui Yang, Ruomeng Ding, Yong Lin, et al.
  18.19
• Pku-saferlhf: Towards Multi-level Safety Alignment For Llms With Human Preference (2024)
  Jiaming Ji, Donghai Hong, Borong Zhang, et al.
  18.18
• Agentic Reward Modeling: Integrating Human Preferences With Verifiable Correctness Signals For Reliable Reward Systems (2025)
  Hao Peng, Yunjia Qi, Xiaozhi Wang, et al.
  17.49
• Improving Large Language Models Via Fine-grained Reinforcement Learning With Minimum Editing Constraint (2024)
  Zhipeng Chen, Kun Zhou, Wayne Xin Zhao, et al.
  17.37
• Aligning Large Language Models With Human Preferences Through Representation Engineering (2023)
  Wenhao Liu, Xiaohua Wang, Muling Wu, et al.
  16.98
• Defending Large Language Models Against Jailbreak Attacks Via Layer-specific Editing (2024)
  Wei Zhao, Zhe Li, Yige Li, et al.
  16.94
• Reason For Future, Act For Now: A Principled Framework For Autonomous LLM Agents With Provable Sample Efficiency (2023)
  Zhihan Liu, Hao Hu, Shenao Zhang, et al.
  16.93
• When Is Tree Search Useful For LLM Planning? It Depends On The Discriminator (2024)
  Ziru Chen, Michael White, Raymond Mooney, et al.
  16.92
• Inferaligner: Inference-time Alignment For Harmlessness Through Cross-model Guidance (2024)
  Pengyu Wang, Dong Zhang, Linyang Li, et al.
  16.83
• Iterative Nash Policy Optimization: Aligning Llms With General Preferences Via No-regret Learning (2024)
  Yuheng Zhang, Dian Yu, Baolin Peng, et al.
  16.80
• Steerlm: Attribute Conditioned SFT As An (user-steerable) Alternative To RLHF (2023)
  Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, et al.
  16.77
• Formal-llm: Integrating Formal Language And Natural Language For Controllable Llm-based Agents (2024)
  Zelong Li, Wenyue Hua, Hao Wang, et al.
  16.74
• Archer: Training Language Model Agents Via Hierarchical Multi-turn RL (2024)
  Yifei Zhou, Andrea Zanette, Jiayi Pan, et al.
  16.61
• Self-explore: Enhancing Mathematical Reasoning In Language Models With Fine-grained Rewards (2024)
  Hyeonbin Hwang, Doyoung Kim, Seungone Kim, et al.
  16.59
• Let's Reward Step By Step: Step-level Reward Model As The Navigators For Reasoning (2023)
  Qianli Ma, Haotian Zhou, Tingkai Liu, et al.
  16.52
• Pairwise Proximal Policy Optimization: Harnessing Relative Feedback For LLM Alignment (2023)
  Tianhao Wu, Banghua Zhu, Ruoyu Zhang, et al.
  16.51
• Hiagent: Hierarchical Working Memory Management For Solving Long-horizon Agent Tasks With Large Language Model (2024)
  Mengkang Hu, Tianxing Chen, Qiguang Chen, et al.
  16.39
• Real: Efficient RLHF Training Of Large Language Models With Parameter Reallocation (2024)
  Zhiyu Mei, Wei Fu, Kaiwei Li, et al.
  16.34
• Language Agents With Reinforcement Learning For Strategic Play In The Werewolf Game (2023)
  Zelai Xu, Chao Yu, Fei Fang, et al.
  16.23
• Arithmetic Control Of Llms For Diverse User Preferences: Directional Preference Alignment With Multi-objective Rewards (2024)
  Haoxiang Wang, Yong Lin, Wei Xiong, et al.
  16.19