Reflexion: Language Agents with Verbal Reinforcement Learning

作者： Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao (2023)

arXiv： 2303.11366

领域

应用

TLDR（中文）

让 agent 在失败后用自然语言做"复盘"，下一轮把反思塞进 prompt。"无梯度的自我改进"思路被广泛复用于 coding agent、SWE-agent。

TLDR (English)

Makes agent do natural language "post-mortem" after failure, injecting reflection into next round's prompt. "Gradient-free self-improvement" approach widely reused in coding agents, SWE-agent.

出现在这些文章里

• Agent 与工具使用：模型不只是聊天
• Agents and Tool Use: Models Are More Than Chat

同被引用

这些论文与本文出现在同一篇文章中

• Model Context Protocol (MCP) Anthropic (2024)
• Toolformer: Language Models Can Teach Themselves to Use Tools Timo Schick et al. (2023)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Yang et al. (2024)
• ReAct: Synergizing Reasoning and Acting in Language Models Shunyu Yao et al. (2022)

相关论文

同一领域的其他论文

• Model Context Protocol (MCP) Anthropic (2024)
  应用
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues? Carlos E. Jimenez et al. (2024)
  评估应用
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Yang et al. (2024)
  应用
• Toolformer: Language Models Can Teach Themselves to Use Tools Timo Schick et al. (2023)
  应用
• Efficient Guided Generation for Large Language Models Brandon T. Willard et al. (2023)
  推理应用
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models Shunyu Yao et al. (2023)
  推理能力应用