Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization

作者：Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, Weiming Lu · 单位：College of Computer Science and Technology, Zhejiang University, Institute of Software, Chinese Academy of Sciences, Nanjing Institute of Software Technology, Nanjing University of Posts and Telecommunications, Nanjing University of Information Science and Technology · 会议/期刊：ACL 2024 · 分类：规划与操作 · 发布日期：2024