Advances in Neural Information Processing Systems 37 / 模仿与示范学习

Recursive Introspection: Teaching Language Model Agents How to Self-Improve

作者：Yuxiao Qu, Tianjun Zhang, Naman Garg, Aviral Kumar · 单位：Carnegie Mellon University, UC Berkeley · 会议/期刊：Advances in Neural Information Processing Systems 37 · 方向：模仿与示范学习 · 发布日期：2024-07-25

自我进化智能体模仿与示范学习大语言模型智能体模型自进化模仿学习
新标签打开 AlphaXiv新标签打开 Code
Recursive Introspection: Teaching Language Model Agents How to Self-Improve figure
AlphaXiv 中文概览（可滚动查看）