RL for LLM Agents

RL: Reinforcement Learning · LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

70 papers in the last four weeks, up 141% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 402

All topics

Healthcare AI GYM for Medical Agents
May 1, 2026Minbyul JeongHealthcare On-Policy Distillation
Upstage AI
AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
May 1, 2026Haotian Zhao, Songlin Zhou, Yuxin Zhang +9Agentic RL Credit Assignment in RL
Baidu · Tsinghua University · Fudan University
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Apr 30, 2026Eyon Jang, Damon Falck, Joschka Braun +6RL Exploration LLM Safety
MATS · UC San Diego · Anthropic +1
Rethinking Agentic Reinforcement Learning In Large Language Models
Apr 30, 2026Fangming Cui, Ruixiao Zhu, Cheng Fang +2RL for Language Models Agentic RL
Beijing, China · Shanghai, China
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
DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents
Apr 27, 2026Junshuo Zhang, Chengrui Huang, Feng Guo +6Reinforcement Learning RL Exploration
University of Electronic Science and Technology of China · DiDi
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
Apr 27, 2026Zhisong Qiu, Shuofei Qiao, Kewei Xu +4Process Reward Models RL for LLM Agents
Zhejiang University Ant Group Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph Hangzhou, China · Zhejiang University Hangzhou, China · Ant Group Hangzhou, China +2
JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
Apr 26, 2026Zhengding Hu, Hehua Ouyang, Chang Chen +6RL Post-Training Pipeline Parallelism
University of California, San Diego
Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
Apr 22, 2026Yuxuan Cai, Wei Li, Jie Zhou +4Lifelong Learning Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
Apr 21, 2026Shengqin Wang, Wentao Yan, Huichi Zhou +4Reward Shaping RL for Language Model Reasoning
East China Normal University · University College London · Huawei Noah’s Ark Lab +2
SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution
Apr 21, 2026Xiachong Feng, Yi Jiang, Xiaocheng Feng +9Credit Assignment in RL Step-Level Credit Assignment in RL
The University of Hong Kong · Harbin Institute of Technology · Harbin Institute of Technology, Shenzhen
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
Apr 20, 2026Daoyu Wang, Qingchuan Li, Mingyue Cheng +4Agentic RL Credit Assignment in RL
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Apr 20, 2026Guanting Dong, Junting Lu, Junjie Huang +17Lifelong Learning Agents AI Agent Benchmarks
Renmin University of China · ByteDance Seed
CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
Apr 19, 2026Hansi Zeng, Liam Collins, Bhuvesh Kumar +2Reinforcement Learning Learning to Rank
Center for Intelligent Information Retrieval, University of Massachusetts Amherst · Snap Inc.
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
Apr 19, 2026Jingbo Sun, Wenyue Chong, Songjun Tu +7Agentic Retrieval Agentic RAG
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences +1
Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
Apr 18, 2026Weiyu Ma, Yongcheng Zeng, Yan Song +4Reinforcement Learning RL Post-Training
King Abdullah University of Science and Technology (KAUST) · Chinese Academy of Sciences, Institute of Automation (CASIA) · AI Centre, Department of Computer Science, University College London +1
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
Apr 17, 2026Shidong Yang, Ziyu Ma, Tongwen Huang +3LLM Agent Training RL for LLM Agents
AMAP, Alibaba Group
"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations
Apr 16, 2026Yang Wu, Jinhong Yu, Jingwei Xiong +2AI-Assisted Scientific Research LLM Agents
Worcester Polytechnic Institute, Worcester, MA, USA · University of California, Davis, CA, USA · Jiangsu University, Zhenjiang, Jiangsu, China
Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
Apr 16, 2026Zhiyuan Zhai, Wenjing Yan, Xiaodan Shao +1LLM Agent Training RL for LLM Agents
Fudan University · Chinese University of Hong Kong · University of Waterloo
Mind DeepResearch Technical Report
Apr 16, 2026MindDR Team, Li Auto IncMulti-Agent LLM Systems Deep Research Agents
MindDR Team, Li Auto Inc
OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
Apr 13, 2026Kun Liu, Liqun ChenAI Alignment RL for LLM Agents
TRACE: Capability-Targeted Agentic Training
Apr 7, 2026Hangoo Kang, Tarun Suresh, Jon Saad-Falcon +1LLM Agent Self-Improvement Agent Skill Learning
Stanford University
Marginal-Contribution Policy Gradients under Filtered Feedback for Multi-Agent LLMs
Apr 3, 2026Elai Ben-Gal, Stela TongMulti-Agent LLM Systems Multi-Agent System Optimization
Department of Mathematics Stanford University · Graduate School of Business Stanford University
Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation
Mar 18, 2026Philipp Normann, Andreas Happe, Jürgen Cito +1LLM Agent Security LLM Post-Training
TU Wien, Vienna, Austria
Complementary RL: Towards Efficient Experience-Driven Agent Learning
Mar 18, 2026Dilxat Muhtar, Jiashun Liu, Wei Gao +8Reinforcement Learning Sample-Efficient RL
Alibaba Group · HKUST
Agentic Critical Training
Mar 9, 2026Weize Liu, Minghui Liu, Sy-Tuyen Ho +5LLM Agent Training Imitation Learning
University of Maryland, College Park
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
Feb 13, 2026Kehao Zhang, Shangtong Gui, Sheng Yang +2Persistent Memory for Language Models Long-Context Inference
1Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS) · University of Chinese Academy of Sciences, Beijing, China · 4Li Auto Inc. +1
TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
Feb 12, 2026Aladin Djuhera, Swanand Kadhe, Farhan Ahmed +3Tree Search LLM Agent Training
Technical University Munich · IBM Research
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Feb 9, 2026Lang Feng, Longtao Zheng, Shuo He +2Multi-Agent LLM Systems Multi-Agent System Optimization
Nanyang Technological University, Singapore
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Feb 9, 2026Peng Xia, Jianwen Chen, Hanyang Wang +10LLM Agent Skill Learning RL for LLM Agents
UNC-Chapel Hill · University of Chicago · University of California San Diego +3

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

Healthcare AI GYM for Medical Agents

Minbyul Jeong

Upstage AI

Healthcare On-Policy Distillation Medical LLMs RL for LLM Agents Agent Benchmarks RL for Tool Use

Open paper AskPDF arXiv

Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisions -- yet a unified training environment provides the breadth of clinical domains and specialized tools to train generalizable medical AI agents through reinforcement learning remains elusive. We present a comprehensive empirical study of multi-turn agentic RL for medical AI, built on \gym{}, a gymnasium-compatible environment spanning 10 clinical domains with 3.6K+ tasks, 135 domain-specific tools, and a knowledge base of 828K medical passages. Our analysis reveals that agentic multi-turn structure degrades into verbose single-turn monologues, characterized by monotonic length explosion and a simultaneous erosion of tool-use frequency. We characterize how this collapse, alongside distillation instability, stems from the misalignment of sparse terminal rewards with sequential clinical trajectories. We find that vanilla GRPO achieves strong final accuracy on some benchmarks but suffers from training instability, evidenced by significant oscillations in response length and prolonged convergence periods. To improve training efficiency and stability, we propose Turn-level Truncated On-Policy Distillation (TT-OPD), a self-distillation framework where a gradient-free EMA teacher leverages outcome-privileged information to provide dense, outcome-aware KL regularization at every conversation turn. TT-OPD achieves the best performance on 10 of 18 benchmarks with an average +3.9~pp improvement over the non-RL baseline with faster early convergence, controlled response length, and sustained multi-turn tool use.

Momentum

Related topics

Latest papers 402