RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
Abstract
Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in static tasks, multi-turn agent RL training remains underexplored. We propose StarPO (State-Thinking-Actions-Reward Policy Optimization), a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents. Our study on three stylized environments reveals three core findings. First, our agent RL training shows a recurring mode of Echo Trap where reward variance cliffs and gradient spikes; we address this with StarPO-S, a stabilized variant with trajectory filtering, critic incorporation, and decoupled clipping. Second, we find the shaping of RL rollouts would benefit from diverse initial states, medium interaction granularity and more frequent sampling. Third, we show that without fine-grained, reasoning-aware reward signals, agent reasoning hardly emerge through multi-turn RL and they may show shallow strategies or hallucinated thoughts. Code and environments are available at https://github.com/RAGEN-AI/RAGEN.
Community
Project website: https://ragen-ai.github.io
Code and environments are available at https://github.com/RAGEN-AI/RAGEN.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce (2025)
- Learning to Reason under Off-Policy Guidance (2025)
- ToolRL: Reward is All Tool Learning Needs (2025)
- Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning (2025)
- A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization (2025)
- VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks (2025)
- GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper