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.

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
Mar 5, 2026Karan Gupta, Pranav Vajreshwari, Yash Pandya +3RL for Tool Use Agentic RL
Microsoft Research
RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization
Mar 3, 2026Siwei Zhang, Yun Xiong, Xi Chen +4Agentic RL RL for Language Model Reasoning
Fudan University · Zhejiang University · UC Davis
Selection as Power: Constrained Reinforcement for Bounded Decision Authority
Mar 2, 2026Jose Manuel de la Chica Rodriguez, Juan Manuel Vera DíazAI Agent Governance Constrained RL
AI Lab, Grupo Santander Madrid, Spain
Federated Agentic AI for Wireless Networks: Fundamentals, Approaches, and Applications
Mar 2, 2026Lingyi Cai, Yu Zhang, Ruichen Zhang +5Wireless Communications Agentic RL
Research Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China · College of Computing and Data Science, Nanyang Technological University, Singapore · School of Engineering, Edith Cowan University, Perth, WA 6027, and the School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW 2033, Australia +2
HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents
Mar 1, 2026Hongbo Jin, Rongpeng Zhu, Jiayu Ding +2Long-Horizon LLM Agents Long-Horizon Agent Tasks
School of Electronic and Computer Engineering, Peking University
RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
Feb 28, 2026Andrew Zhuoer Feng, Cunxiang Wang, Bosi Wen +4RL for Language Models Reward Design for RL
Tsinghua Univeristy · Peking University
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Feb 27, 2026Weinan Dai, Hanlin Wu, Qiying Yu +13GPU Kernel Generation GPU Kernel Optimization
ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University · SIA-Lab of Tsinghua AIR and ByteDance Seed
Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
Feb 26, 2026Shuo He, Lang Feng, Qi Wei +3Agentic RL RL for LLM Agents
Nanyang Technological University · Southeast University
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
Feb 25, 2026Xiaoxuan Wang, Han Zhang, Haixin Wang +11Agentic RL Reinforcement Learning
Department of Computer Science, University of California, Los Angeles, California, USA · University of Wisconsin–Madison, Madison, Wisconsin, USA
PyVision-RL: Forging Open Agentic Vision Models via RL
Feb 24, 2026Shitian Zhao, Shaoheng Lin, Ming Li +4Adaptive Video Frame Sampling Multimodal Agents
Shanghai AI Lab · UMD · CUHK +3
Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
Feb 19, 2026Shengtian Yang, Yu Li, Shuo He +4Reinforcement Learning RL for LLM Agents
School of Computer Science and Engineering, Southeast University, Nanjing, China · Kuaishou Technology, Beijing, China · College of Computing and Data Science, Nanyang Technological University, Singapore
LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
Feb 18, 2026Hejia Zhang, Zhongming Yu, Chia-Tung Ho +3LLM Agent Training Automated Test Generation
University of California San Diego, USA · NVIDIA · Agentrys
GLM-5: from Vibe Coding to Agentic Engineering
Feb 17, 2026GLM-5-Team, :, Aohan Zeng +184LLM Agent Training Agentic RL
Learning to Configure Agentic AI Systems
Feb 12, 2026Aditya Taparia, Som Sagar, Ransalu SenanayakeLLM Agent Workflow Optimization Agentic RL
School of Computing and Augmented Intelligence Arizona State University Tempe, AZ, USA
Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
Feb 11, 2026Yihang Yao, Zhepeng Cen, Haohong Lin +6Agentic RL LLM Agents
Carnegie Mellon University · Salesforce AI Research · Massachusetts Institute of Technology +2
CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
Jan 21, 2026Tianshi Xu, Yuteng Chen, Meng LiAgentic RL Reinforcement Learning
Peking University · NTU, Singapore
PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization
Jan 15, 2026Tingyue Pan, Jie Ouyang, Mingyue Cheng +7Agentic RL Policy Optimization
State Key Lab of Cognitive Intelligence, University of Science and Technology of China
OpenTinker: Separating Concerns in Agentic Reinforcement Learning
Jan 12, 2026Siqi Zhu, Jiaxuan YouAgentic RL LLM Agent Training
University of Illinois Urbana-Champaign
LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach
Oct 13, 2025Renxuan Tan, Rongpeng Li, Fei Wang +4Agentic RL Stackelberg Games
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China · Huawei Technologies Company Ltd., Shanghai 210026, China · Zhejiang Lab as well as Zhejiang University, Hangzhou 310027, China +1
DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
Sep 26, 2025Yansong Ning, Rui Liu, Jun Wang +6Agentic RL Travel Planning
The Hong Kong University of Science and Technology (Guangzhou) · Didichuxing Co. Ltd
AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System
Jul 20, 2025Renxi Wang, Bilal El Bouardi, Rifo Ahmad Genadi +6Agentic RL LLM Agent Training
Mohamed bin Zayed University of Artificial Intelligence · University of California, Los Angeles
Agentic Episodic Control
Jun 2, 2025Xidong Yang, Wenhao Li, Junjie Sheng +4Agentic RL Reinforcement Learning
East China Normal University · Tongji University · Shanghai Jiao Tong University +2

Mar 5, 2026J/K move · Enter open · S save

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Karan Gupta, Pranav Vajreshwari, Yash Pandya, Raghav Magazine+2

Microsoft Research

RL for Tool Use Agentic RL RL Fine-Tuning LLM Context Management Rubric-Based RL

Open paper AskPDF arXiv

Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small language models (SLMs) remain brittle: eager tool loading saturates context, execution errors compound over time, and sparse rewards limit learning. We introduce ATLAS, a reinforcement finetuning framework that enables SLMs to operate effectively in large-scale toolspace environments by learning how to acquire context and how to execute actions. Our approach makes two key contributions. First, we treat context control and execution structure as learnable decisions, combining iterative tool loading with programmatic tool orchestration to bound context growth and stabilize long-horizon trajectories. Second, we propose rubric-based reinforcement finetuning, which decomposes task success into structured, task-aligned criteria and enables scalable training using small judge models. Across MCP benchmarks, these design choices yield large and consistent gains over generic RL baselines, allowing a 4B SLM to approach frontier-agent performance under far tighter parameter and context budgets.