# 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](Search-R1：Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.md)

### [WebThinker：Empowering Large Reasoning Models with Deep Research Capability](WebThinker：Empowering Large Reasoning Models with Deep Research Capability.md)

### [ZEROSEARCH：Incentivize the Search Capability of LLMs without Searching](ZEROSEARCH：Incentivize the Search Capability of LLMs without Searching.md)

### [AGENTIC REINFORCED POLICY OPTIMIZATION](AGENTIC REINFORCED POLICY OPTIMIZATION.md)

### [Search and Refine During Think：Autonomous Retrieval - Augmented Reasoning of LLMs](Search and Refine During Think：Autonomous Retrieval - Augmented Reasoning of LLMs.md)

## 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](../Planning/RLVMR：Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents.md)

### [Group-in-Group Policy Optimization for LLM Agent Training](../Planning/Group-in-Group Policy Optimization for LLM Agent Training.md)

### [Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning](Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning.md)

## 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](https://zhuanlan.zhihu.com/p/1902381952998281700)