# Reinforcement learning for LLM agents Area: [LLM agents and tool use](https://mlsanity.com/agents/index.md). HTML: https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/ ## Key facts - Reinforcement learning for LLM agents: 850 papers on arXiv since 2022 (data through 14 Oct 2026). - 159 of its 850 mapped papers (19%) cite “Reflexion: Language Agents with Verbal Reinforcement Learning” (2023, arXiv 2303.11366). - 151 of its 850 mapped papers (18%) cite “Group-in-Group Policy Optimization for LLM Agent Training” (2025, arXiv 2505.10978). - 165 new papers 17 Sep–14 Oct. ## Most cited here - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023), cited by 159 papers here - [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025), cited by 151 papers here - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023), cited by 135 papers here - [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025), cited by 103 papers here - [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025), cited by 86 papers here - [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025), cited by 84 papers here - [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022), cited by 65 papers here - [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025), cited by 52 papers here - [ToRL: Scaling Tool-Integrated RL](https://mlsanity.com/paper/2503.23383/) (2025), cited by 51 papers here - [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024), cited by 50 papers here ## New (17 Sep–14 Oct) - [Co-Evolving Acting and Forecasting for Language Agents](https://mlsanity.com/paper/2610.20597/) (2026-10-14) - [Player-1: Learning to Play from Synthetic Experience](https://mlsanity.com/paper/2610.20584/) (2026-10-14) - [One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness](https://mlsanity.com/paper/2610.20576/) (2026-10-14) - [Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards](https://mlsanity.com/paper/2610.19868/) (2026-10-14) - [ActionOPD: Distilling Decisions, Not Tokens](https://mlsanity.com/paper/2610.19820/) (2026-10-14) - [More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.19789/) (2026-10-14) - [Model What Matters: Decision-Guided Selective World Modeling for Language Agents](https://mlsanity.com/paper/2610.19642/) (2026-10-14) - [Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories](https://mlsanity.com/paper/2610.19614/) (2026-10-14) - [From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents](https://mlsanity.com/paper/2610.19420/) (2026-10-14) - [SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.19397/) (2026-10-14) - [Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents](https://mlsanity.com/paper/2610.19349/) (2026-10-14) - [Verifier-Grounded Agentic RL for Provably Correct Code](https://mlsanity.com/paper/2610.19298/) (2026-10-13) - [Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models](https://mlsanity.com/paper/2610.19271/) (2026-10-13) - [Contextual Credit Policy Optimization](https://mlsanity.com/paper/2610.19103/) (2026-10-13) - [Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards](https://mlsanity.com/paper/2610.18868/) (2026-10-13) - [SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection](https://mlsanity.com/paper/2610.18807/) (2026-10-13) - [SEAR: Self-Evolving Agentic Robotics](https://mlsanity.com/paper/2610.18792/) (2026-10-13) - [ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.18683/) (2026-10-13) - [Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints](https://mlsanity.com/paper/2610.18459/) (2026-10-13) - [Choosing LLMs for Strategic Agent Interactions](https://mlsanity.com/paper/2610.18354/) (2026-10-13) - [TextualRL: Textual Reinforcement Learning for Context Management](https://mlsanity.com/paper/2610.18216/) (2026-10-13) - [Agent-Reflex: Teaching Language Agents to Act Reflectively](https://mlsanity.com/paper/2610.17953/) (2026-10-13) - [Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards](https://mlsanity.com/paper/2610.17893/) (2026-10-13) - [TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training](https://mlsanity.com/paper/2610.17726/) (2026-10-13) - [The belief-action gap in language model agents](https://mlsanity.com/paper/2610.17444/) (2026-10-12) - [Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models](https://mlsanity.com/paper/2610.17310/) (2026-10-12) - [Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.16592/) (2026-10-12) - [EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents](https://mlsanity.com/paper/2610.16523/) (2026-10-12) - [A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes](https://mlsanity.com/paper/2610.16352/) (2026-10-12) - [Heterogeneous Agentic Coevolution](https://mlsanity.com/paper/2610.16078/) (2026-10-12)