Reflexion: Language Agents with Verbal Reinforcement Learning

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

arXiv: 2303.11366

Domains

Applications

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.

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。

Appears in These Articles

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

Co-cited Papers

These papers appear in the same articles as this one

• 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)

Related Papers

Other papers in the same domain

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