agent RL相关论文

tool-use

通过RL提高模型调用工具的能力。 ### Search-R1：Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

WebThinker：Empowering Large Reasoning Models with Deep Research Capability

ZEROSEARCH：Incentivize the Search Capability of LLMs without Searching

AGENTIC REINFORCED POLICY OPTIMIZATION

Search and Refine During Think：Autonomous Retrieval - Augmented Reasoning of LLMs

planning

通过RL提高长程规划能力，一般都会针对信用分配问题进行解决。 ### RLVMR：Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents

Group-in-Group Policy Optimization for LLM Agent Training

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

参考

# 2025年大模型agent rl训练多轮planning技术TORL,ToolRL, RAGEN,OTC,SkyRL-v0, GiGPO,Tool-N1 ,ARTIST, ZeroTIR, GRPO