ReAct：语言模型中推理与行动的协同

Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao

论文 2022 原文 2022-10-06 ICLR 2023 arXiv:2210.03629 收录 2026-09-06 reasoningtool-usefoundation

摘要

提出 ReAct 范式：让大模型交替进行推理链思考与外部行动，成为绝大多数智能体框架的范式基础。

引用本文条目

GB/T 7714-2015

Shunyu Yao, Jeffrey Zhao, Dian Yu, et al. ReAct: Synergizing Reasoning and Acting in Language Models[EB/OL]. ICLR 2023, 2022(2022-10-06)[2026-09-16]. https://arxiv.org/abs/2210.03629.

BibTeX

@misc{yao2022,
  author = {Shunyu Yao and Jeffrey Zhao and Dian Yu and Nan Du and Izhak Shafran and Karthik Narasimhan and Yuan Cao},
  title = {ReAct: Synergizing Reasoning and Acting in Language Models},
  year = {2022},
  organization = {ICLR 2023},
  howpublished = {\url{https://arxiv.org/abs/2210.03629}},
}

查看原文 ↗

本条目为「智联观察」资料库收录，引用时请注明来源与本页链接。