ReAct: Synergizing Reasoning and Acting in Language Models

作者： Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao (2022)

arXiv： 2210.03629

领域

应用

TLDR（中文）

ReAct 框架将推理（Reasoning）和行动（Acting）交织在一起：LLM 先思考（Thought）， 再执行工具调用（Action），观察结果（Observation），如此循环。这是现代 AI Agent 框架的原型，直接影响了 LangChain、AutoGPT 等 agent 框架的设计。

TLDR (English)

ReAct interleaves reasoning and acting: LLM thinks (Thought), executes a tool call (Action), observes the result (Observation), and cycles. This is the prototype for modern AI agent frameworks, directly influencing LangChain, AutoGPT, and similar agent frameworks.

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)
• Reflexion: Language Agents with Verbal Reinforcement Learning Noah Shinn et al. (2023)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Yang et al. (2024)

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
• Reflexion: Language Agents with Verbal Reinforcement Learning Noah Shinn et al. (2023)
  应用
• Efficient Guided Generation for Large Language Models Brandon T. Willard et al. (2023)
  推理应用