Agentic RL

RL: Reinforcement Learning

Agentic reinforcement learning studies how language and multimodal models can learn to act over multiple steps in environments, using tools, memory, and feedback to complete tasks. Common approaches extend policy-gradient methods such as PPO and GRPO with process rewards, step-level credit assignment, exploration strategies, and skill or experience reuse; some also use teacher guidance or learned world models. Training and evaluation span simulated and executable tool environments, web and coding tasks, embodied control, and real-world workflows, with systems work addressing the cost of generating long interaction trajectories. A central challenge is balancing sparse or imperfect outcome signals against fine-grained supervision while keeping learning stable, efficient, and robust beyond the training environment.

Latest papers

232 papers63 papers in the last four weeks, up 294% on the four weeks before. 0.4% of all new papers.

SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
Oct 28, 2026Qirui Liu, Wei Cao, Yu Mi +5Agentic RL On-Policy Self-Distillation
Zhejiang University · Ant Group
EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning
Oct 27, 2026Sihan Yang, Weichen Bai, Ruichuan An +9Agentic RL Reinforcement Learning
PKU · XJTU · THU +3
Action-Value Calibration via Continuation Sharing for Long-Horizon Agentic Reinforcement Learning
Oct 27, 2026Yingjian Chen, Lang Zhou, Zixin Zhao +3Agentic RL Step-Level Credit Assignment in RL
Sun Yat-sen University · Shenzhen Loop Area Institute
When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing
Oct 26, 2026Lei Zhao, Zongheng Cao, Xinyu HuReinforcement Learning Fine-Grained Credit Assignment
University of Pennsylvania · Philo Labs
InterQ-RL: Interaction-Aware Correction of Execution Mismatch in Quantized Agentic RL
Oct 26, 2026Yingbo Hao, Song Liu, Guanghua Yu +3Reinforcement Learning Agentic RL
South China University of Technology · Tencent
From Human Intent to In-Orbit Action: A Self-Learning Large Language Model Agent for 6G Satellite Networks
Oct 25, 2026Zhengqian Xu, Yasheng Zhang, Chenhua Sun +2LEO Satellite Networks 6G Networks
The 54th Research Institute of China Electronics Technology Group Corporation (CETC-54)
Same Luck, Different Choice: Twin-World Credit Assignment for Agentic Reinforcement Learning
Oct 22, 2026Zeropy Surio, Tobias Engel, Mei-Lin Chou +2Step-Level Credit Assignment in RL Counterfactual Credit Assignment
University of Sheffield · Carnegie Mellon University · University of Michigan
Harness Scaling for Generalizable Agentic Reinforcement Learning
Oct 21, 2026Fei Bai, Huatong Song, Chuan Hao +5Agentic RL LLM Agent Harnesses
Gaoling School of Artificial Intelligence, Renmin University of China · IQuest Research · Beihang University
BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
Oct 21, 2026Ge Qu, Jinyang Li, Xiaohan Xu +6Agentic RL RL for LLM Agents
The University of Hong Kong · National University of Singapore · The Chinese University of Hong Kong, Shenzhen
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
Oct 20, 2026Xinxin Liu, Bingxin Xu, Wenrui Bao +4Large Language Model-Based Robot Planning RL for Robotics
University of Central Florida · University of Southern California · Michigan State University
Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation
Oct 20, 2026Shu Zhao, Tan YuOn-Policy Distillation RL for LLM Agents
NVIDIA
Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling
Oct 20, 2026Fangcong Yin, Ming Yin, Tanvi Bhandarkar +7Agentic RL Step-Level Credit Assignment in RL
Meta · New York University · Duke University
Trackable Skill Library Lifecycle Management for Agentic Reinforcement Learning
Oct 18, 2026Xi Zhu, Yuanlin Duan, Changyi Yang +4LLM Agent Skill Learning Agentic RL
Rutgers University · Carnegie Mellon University · TikTok Inc.
Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
Oct 18, 2026Jike Zhong, Ming Li, Yuxiang Lai +9On-Policy Distillation Agentic RL
University of Southern California · University of Florida · Emory University +6
WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning
Oct 16, 2026Zijun Dou, Zhen Yang, Xijun Liu +3AI Coding Agents Agentic RL
Tsinghua University · Zhipu AI · Beihang University +1
Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL
Oct 16, 2026Yibin Huang, Conghui ZhuAgentic RL Step-Level Credit Assignment in RL
Faculty of Computing, Harbin Institute of Technology
X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
Oct 15, 2026Adhwaa Al-Chaab, Ayman Younis, Dario PompiliNetwork Slicing Agentic RL
†Department of Electrical and Computer Engineering, Rutgers University–New Brunswick, NJ, USA
Mosaic: Multi-Session Agentic Reinforcement Learning
Oct 15, 2026Yilong Xu, Minrui Xu, Xinyu Zhou +3Agentic RL RL for LLM Agents
LARK, HKUST(GZ) · Foundation Model Lab, Huawei · City University of Hong Kong +1
Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards
Oct 15, 2026Ruida Wang, Gerald Friedland, Tong Zhang +1Agentic RL RL for Tool Use
Amazon Web Services · University of Illinois Urbana-Champaign
ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
Oct 15, 2026Yukun Tian, Junwei Su, Haofeng Xu +6RL Post-Training RL for Language Model Reasoning
The University of Hong Kong · Alibaba Group · University of Science and Technology of China +1
OpCredit: Operation-Aware Policy Learning for Agentic Knowledge Graph Question Answering
Oct 15, 2026Yucheng Li, Mingyuan Li, Xiaxia Wang +1Knowledge Graph Question Answering Policy Learning
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · Department of Computer Science, University of Oxford
Co-Evolving Acting and Forecasting for Language Agents
Oct 14, 2026Haofei Yu, Yixing Chen, Yining Zhao +6RL for LLM Agents Agentic RL
University of Illinois Urbana-Champaign · University of California San Diego · Meta AI
CASI: Credit Assignment via Set Intervention for Agentic Retrieval
Oct 14, 2026Xinyi Cheng, Tianfu Zhang, Jiwen Li +5Credit Assignment Fine-Grained Credit Assignment
Xiaohongshu Inc.
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
Oct 14, 2026Linhao Zhong, Bozhen Fang, Xuehao Wang +7Agentic RL Self-Distillation
Zhejiang University, State Lab of CAD & CG · Ant Group
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
Oct 14, 2026Dingyi Rong, Yue Shi, Chaofan Ma +5Reinforcement Learning Agentic RL
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Tongji University
Verifier-Grounded Agentic RL for Provably Correct Code
Oct 13, 2026George Ma, Yuhao Zhang, Bing He +5RL for Code Generation Verified Code Generation
UC Berkeley · AWS AI Labs
SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection
Oct 13, 2026Wenlin Zhong, Hao Wang, Kun Yuan +6Reinforcement Learning Agentic RL
Zhejiang University · Kuaishou Technology · University of the Chinese Academy of Sciences +1
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
Oct 13, 2026Bowen Ding, Mingda Wan, Yuhan Chen +7Agentic RL Reinforcement Learning
Zhejiang University · School of Engineering, Westlake University · Huawei Noah’s Ark Lab +1
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Oct 13, 2026Hang He, Linting Wang, Guanming Liu +14LLM Agent Training Long-Horizon LLM Agents
Agent-Reflex: Teaching Language Agents to Act Reflectively
Oct 13, 2026Guanting Dong, Xinyu Yang, Jiajie Jin +9LLM Agent Training Self-Reflection in Language Model Agents
Gaoling School of Artificial Intelligence, Renmin University of China · National University of Singapore

Oct 28, 2026J/K move · Enter open · S save

SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning

Qirui Liu, Wei Cao, Yu Mi, Yichen Sun+4

Zhejiang University · Ant Group

Agentic RL On-Policy Self-Distillation RL for Knowledge Distillation

Open paper AskPDF arXiv

Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed trajectories may contain correct steps, while successful trajectories can contain errors. Trajectory-level skills can also shift teacher preferences at unrelated steps, introducing off-target distillation signals. We introduce SCOPE, a framework for Selective Critical-Step On-Policy Self-Distillation. After a supervised warm-up, the policy analyzes its own trajectories, generates step-specific hindsight skills, and distills their guidance only at selected error steps. A bounded signed teacher-student coefficient stabilizes auxiliary updates while preserving positive reinforcement and negative correction. A success-relative pairwise length reward further encourages efficient task completion. Experiments on ALFWorld and WebShop demonstrate consistent improvements across multiple model backbones. With Qwen2.5-3B, SCOPE achieves 97.7% success on ALFWorld and 85.2% on WebShop, outperforming SEED by 5.9 and 6.3 percentage points, respectively. On unseen ALFWorld tasks, SCOPE reaches 89.6% success, improving over GRPO by 23.2 percentage points with 46.7% fewer interactions. Scaling to Qwen3-32B, SCOPE achieves 99.2% success on seen ALFWorld tasks and 94.0% on unseen tasks.