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

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents
Aug 2, 2026Jianan Xie, Xin Sun, Zhongqi Chen +4Agentic Search Credit Assignment in RL
ShanghaiTech University · NLPR, MAIS, CASIA · Ant Group
BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent
Aug 2, 2026Yibin Huang, Bin Xu, Hailong Cao +1Process Reward Models Credit Assignment in RL
Faculty of Computing, Harbin Institute of Technology
Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering
Aug 2, 2026Aounon Kumar, Sudipta Paul, Vivek Kulkarni +2Multi-Hop QA Agentic RAG
AI Center-Mountain View, Samsung Electronics
PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent
Aug 2, 2026Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni +4Reward Shaping LLM-Guided RL
AI Center-Mountain View, Samsung Electronics
SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
Aug 1, 2026Tao Liu, Tao Feng, Xiangheng Li +9Reinforcement Learning Text-to-SQL
Zhejiang University, College of Artificial Intelligence · Zhengzhou University, School of Computer Science of Artificial Intelligence · Byte Dance
RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning
Jul 31, 2026Chengbo Liu, Lifang Zhou, Ruijie Yan +8Reward Shaping Offline RL
1Microsoft, Beijing, China · 2Southeast University, Nanjing, China
Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares Certificates
Jul 31, 2026Bohan Chen, Shivam N. Patel, Richard Hoffmann +2LLM Agent Verification Tool-Using Agents
1California Institute of Technology · 2OpenAI
Cross-Benchmark Generalization in Long-Horizon Agents
Jul 31, 2026Sushant Mehta, Logan Ritchie, Liudas Panavas +1Long-Horizon Agent Evaluation RL Post-Training
Surge AI
Scaling Scientific Discovery Environments for Turn-Level Agentic RL
Jul 31, 2026Yucheng Xu, Keyi Zhang, Yuyang Yu +4Process Supervision Large Language Model-Guided Scientific Discovery
Shanghai AI Lab
MemHarness: Memory Is Reconstructed, Not Replayed
Jul 30, 2026Rong Wu, Daocheng Fu, Licheng Wen +10LLM Agent Memory RL for LLM Agents
Zhejiang University · Shanghai Artificial Intelligence Laboratory · Fudan University +4
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
Jul 30, 2026Yash Pandya, Sahil Gupta, Sarthak Harne +10Computer-Use Agent Benchmarks Computer-Use Agents
Microsoft Research · Work done while at Microsoft Research.
TAPO: Transition-Aware Policy Optimization for LLM Agents
Jul 30, 2026Cong Li, Peixi Peng, Yisen Zhao +4Reinforcement Learning RL Post-Training
School of Electronic and Computer Engineering, Peking University · Pengcheng Laboratory
Harness-G: A Graph-Structured Harness for Search Agents
Jul 30, 2026Yanning Hou, Haoyuan Chen, Sihang Zhou +7Graph Retrieval-Augmented Generation Credit Assignment in RL
National University of Defense Technology · Changsha, China
SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis
Jul 29, 2026Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan +5Agent Failure Analysis LLM Agent Self-Improvement
The Hong Kong Polytechnic University · Work done during an internship at Tencent. · Platform and Content Group, Tencent +1
A Control System, a Dataset, and a Recipe for Making Frozen LLM Agents Learn a Domain
Jul 28, 2026Debjyoti PaulAgent Harness Optimization LLM Agent Training
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Jul 28, 2026Yu Wang, Yi-Kai Zhang, Wentao Shi +8Reinforcement Learning Game-Playing Agents
University of Science and Technology of China · 4Meituan, China · 2Nanjing University +1
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Jul 27, 2026Junlin Liu, Jiangwang Chen, Zixin Song +7Multi-Agent LLM Systems Agentic Search
University of Chinese Academy of Sciences · 2Tsinghua University · 3Peking University +3
MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
Jul 27, 2026Yiwen Ma, Songjun Tu, Qichao Zhang +3LLM Agent Memory Persistent Memory for Language Models
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
EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff
Jul 27, 2026Xiao Ma, Zhiquan Hu, Yi Wei +5Reinforcement Learning Agentic RAG
NEXTAI Research Institute, Chery Group
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Jul 24, 2026Siyuan Huang, Pengyu Cheng, Haotian Liu +10RL for Language Model Reasoning LLM Agent Skill Learning
Qwen Large Model Application Team, Alibaba · The Chinese University of Hong Kong · Renmin University of China +5
Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards
Jul 24, 2026Cheng Ruoxi, Ma Haoxuan, Zhang Hongyi +7Retrieval-Augmented Generation LLM Grounding
1Fudan University · 2Tencent · 3Nanjing University +2
OpenForgeRL: Train Harness-native Agents in Any Environment
Jul 23, 2026Xiao Yu, Baolin Peng, Ruize Xu +7Computer-Use Agents LLM Agent Training
Columbia University · Microsoft Research · Dartmouth College
The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works
Jul 23, 2026Yu WangReward Hacking Reward Shaping
Independent researcher
AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
Jul 23, 2026Qinfeng Li, Yuntai Bao, Xinyan Yu +7LLM Agent Memory Policy Learning
1Zhejiang University · 2Washington University in St. Louis · University of Science and Technology of China
Sample-Efficient Learning from Agent Experience
Jul 23, 2026Chenhui Gou, Haoqin Tu, Yunhao Fang +2In-Context RL Language Model Distillation
Monash University · ByteDance Seed
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
Jul 22, 2026Jian Hu, Huiying Li, Hao Zhang +8Agentic RL Reinforcement Learning
NVIDIA
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
Jul 22, 2026Yuan Xiong, Linji Hao, Shizhu He +2AI Agent Safety LLM Agent Safety
The 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 · Peking University, Beijing, China +2
Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
Jul 22, 2026Kaibing Yang, Guangfeng Cai, Shengtian Yang +6Group Relative Policy Optimization RL Exploration
Southeast University · Kuaishou Technology · Work done during an internship at Kuaishou Technology, supervised by Jun Xu. +1
WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning
Jul 19, 2026Ryan Xu, Atlas Zhao, David Bao +1Agentic RL Reinforcement Learning
AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization
Jul 19, 2026Yuejia Dou, Hesong Wang, Xinyu Zhang +6Automated Bidding Large Language Model-Guided Optimization
Gaoling School of Artificial Intelligence, Renmin University of China Beijing, China · Alibaba Group Beijing, China

Aug 2, 2026, cs.CLJ/K move · Enter open · S save

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents

Jianan Xie, Xin Sun, Zhongqi Chen, Xing Zheng+3

ShanghaiTech University · NLPR, MAIS, CASIA · Ant Group

Agentic Search Credit Assignment in RL Reinforcement Learning with Verifiable Rewards Self-Distillation RL for LLM Agents

Open paper AskPDF arXiv

Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contributions of individual actions in a multi-turn search process. We propose EviSD, an evidence-conditioned self-distillation framework that uses instance-level supporting evidence as privileged information for search actions and golden answers as complementary privilege for answer actions. During training, the student samples actions from the original context, while the same model re-scores them as a privileged teacher under an action-aligned context. EviSD converts the detached teacher--student gap into a bounded correction to the outcome-derived GRPO advantage and applies it only to generated action spans. This design localizes privileged guidance while preserving the update direction determined by the outcome reward, without an auxiliary distillation objective or any change at inference time. Across seven question-answering benchmarks and three backbones spanning model scales and generations, EviSD achieves the highest macro-average Exact Match in all evaluated settings, outperforming the strongest compared methods by 1.3--2.3 points while modulating only 6.7%--15.1% of response tokens. Code is available at https://github.com/JiananXie/EviSD.

Momentum

Related topics

Latest papers 402