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

Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training
Sep 27, 2026Xinyu Che, Hang Yan, Yanchen Liu +5World Model Learning RL Post-Training
Xi’an Jiaotong University · University of Southern California · University of the Chinese Academy of Sciences +1
Learning to Sell: Reinforcement Learning for Strategic Large Language Model Agents in Multi-Product Markets
Sep 27, 2026Shuze Daniel Liu, Claire Chen, Jiuqi Wang +2Multi-Agent Negotiation Automated Negotiation
Massachusetts Institute of Technology, Cambridge, Massachusetts, USA · Purdue University, West Lafayette, Indiana, USA · California Institute of Technology, Pasadena, California, USA +2
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Sep 24, 2026Xingyu Wu, Yuchen Yan, Zhengxi Lu +9Long-Horizon LLM Agents RL for LLM Agents
Zhejiang University · Tencent
Rufus-Air: An Open LLM Post-Training Recipe
Sep 24, 2026Chia-Yuan Chang, Renyuan Cheng, Rui Feng +19LLM Fine-Tuning RL for Language Model Reasoning
Amazon
From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents
Sep 24, 2026Xingyu Su, Abhishek Kumar, Qing Ping +5On-Policy Self-Distillation LLM Agent Training
Texas A&M University · AWS AI, Amazon
Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
Sep 24, 2026Xincheng Yao, Haobo Fu, Weiming Liu +1Agentic RL Credit Assignment in RL
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University. · Tencent AI Platform Department. · MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University.
TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation
Sep 23, 2026Geng Chen, Ruotong Pan, Zhirui Yang +9AI Agent Benchmarks User Simulation
Peking University · Kuaishou Technology · Xi’an Jiaotong University +3
Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
Sep 23, 2026Zheng Zhang, Liu Liu, Qi Chai +4Large Language Model-Based Role-Play Simulation Adversarial Scenario Generation
The Hong Kong University of Science and Technology (Guangzhou) · Tencent · Shanghai Jiao Tong University
SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving
Sep 23, 2026Zhilong Ge, Yuting Shao, Yutao Yang +6Tool-Augmented Language Model Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Sep 23, 2026Ming Ma, Yi Zhu, Yiran Zhong +7Agentic RL Credit Assignment in RL
Institute of Neuroscience, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Tongyi Lab, Alibaba Group +2
Reinforcement Learning with Decomposed Subtasks
Sep 22, 2026Mattie Terzolo, Mikolaj Sacha, Ayan Sinha +1Group Relative Policy Optimization Credit Assignment in RL
Upwork
MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning
Sep 22, 2026Kairui Yang, Ziheng Yi, Xunkai Li +4Multi-Agent LLM Systems Multi-Agent Systems
MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents
Sep 21, 2026Ruike Cao, Fanyu Zhao, Fugen Yao +5LLM Agent Memory Memory Agent Benchmarks
University of Science and Technology of China · Qwen Business Unit of Alibaba · Fudan University
Luck Is Not Skill: When Do Paired Rollouts Help Group-Relative RL of LLM Agents?
Sep 21, 2026Nazmus SakibGroup Relative Policy Optimization Policy Gradient Methods
BRAC University, Dhaka, Bangladesh
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Sep 17, 2026Yan Yu, Zhengxi Lu, Yizhou Liu +7Agentic RL On-Policy Distillation
Zhejiang University · Alibaba Group
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Sep 17, 2026Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan +2Supervised Fine-Tuning Reinforcement Learning
University of Maryland · AWS AI Labs
Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
Sep 17, 2026Yingxuan Zhuang, Binhe Yu, Jingxiao Yang +6Group Relative Policy Optimization Policy Optimization
Zhejiang University · University of Science and Technology of China · University of New South Wales
DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum
Sep 17, 2026Haoqiang Kang, Yiming Zhang, Yiyang Guo +5Long-Horizon Planning Long-Horizon Agent Evaluation
UC San Diego · Independent · Johns Hopkins University +1
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
Sep 16, 2026Jiaxuan Jiang, Liyuan He, Zhixuan FangContinual Learning for LLM Agents Multi-Agent Systems
IIIS, Tsinghua University, Beijing, China · Shanghai Qi Zhi Institute, Shanghai, China · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Sep 15, 2026Shuhan Xue, Jianyuan Zhong, Ziyuan Nan +10Continual Learning for LLM Agents AI-Assisted Scientific Research
Interactive Memory Learning for Long-Term Conversations
Sep 15, 2026Cai Ke, Jiangyue Yan, Han Zhang +5Multi-Agent LLM Systems Long-Term Conversational Memory
Harbin Institute of Technology, Shenzhen, China · Pengcheng Laboratory, China
Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation
Sep 14, 2026Hai-Dang Dang, Bao-Yen Pham, Bao Nguyen +2Multi-Agent LLM Systems RL for LLM Agents
Hanoi University of Science and Technology · The Chinese University of Hong Kong · Hanoi University of Industry
Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
Sep 14, 2026Zixiang Chen, Sufeng Niu, Yingchi Liu +23Tool-Augmented Language Model Agents Language Modeling
Salesforce Agentforce & AI Research
VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets
Sep 14, 2026Yu Bai, Yukai Miao, Dawei Wang +8RL Benchmarks Reinforcement Learning
Zhongguancun Laboratory · Tsinghua University · Network Management Center, China Mobile
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Sep 12, 2026Junyao Yang, Yucheng Shi, Zhongzhi Li +4Terminal Agents Long-Horizon Agent Evaluation
Tencent Hy Foundation Model · National University of Singapore · University of Georgia +2
Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning
Sep 11, 2026Taoran Liang, Yang Liu, Shang Luo +10Credit Assignment in RL Step-Level Credit Assignment in RL
Nankai University · Peking University · Supply Chain Tech Team Y, JD.com +2
BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL
Sep 9, 2026Guanqun Zhao, Zijun Xie, Binbin Zheng +3Asynchronous RL Off-Policy RL
Beijing University of Posts and Telecommunications · Baidu Inc. · Peking University +1
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
Sep 8, 2026Hongbang Yuan, Zhuoran Jin, Yixin CaoReinforcement Learning Sparse-Reward RL
1Fudan University · 2CASIA · 3Shanghai Innovation Institute
What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents
Sep 7, 2026Chenqian Le, Jiayi Cheng, Qijia He +3RL for Code Generation Group Relative Policy Optimization
New York University · University of Washington · University of Southern California +2
Iris: Climbing to the Search Frontier
Sep 3, 2026Ziyuan Liu, Hengqi Liu, Zichuan Wang +8Multi-Hop QA Web Search Agents
AllSpark Team

Sep 27, 2026, cs.CLJ/K move · Enter open · S save

Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training

Xinyu Che, Hang Yan, Yanchen Liu, Haochen Liu+4

Xi’an Jiaotong University · University of Southern California · University of the Chinese Academy of Sciences+1

World Model Learning RL Post-Training World Model Evaluation RL for LLM Agents

Open paper AskPDF arXiv

Predicting how an environment will change before acting is a natural route to better decision making for agents. Recent post-training methods therefore require agents to predict the next observation and turn that prediction into a reward or a direct supervision signal, which is called world model. Existing next-observation training methods help the agent to learn the environmental content. However, they additionally involve an optimization process, which may introduce several effects other than learning to predict the world. Consequently, where the performance gain comes from during the training process remains an open question. We answer this research question through replacing true next-observation targets with in-distribution mismatched observations during the training process. Across two interactive text environments, mismatched targets lower prediction accuracy by 15.3-61.6% relative to ground-truth targets, yet retain substantial task gains over the base model. Compared with the base model, trained models consider more candidate actions and exhibit less looping. We also introduce a setting that replaces prediction-based rewards with independent random signals. This training expands task coverage (pass@64) even when the reward carries no environment information. We also generalize this finding to VisualWebArena, where random-reward training raises pass@64 by 14.3% relative to the base model, without observation-matching rewards or an external multimodal teacher for reward construction.

Momentum

Related topics

Latest papers 402