HomeResearch LibraryReAct: Synergizing Reasoning and Acting in Language Mod…
system architectureChapter 1ICLR 2023 · 2023

ReAct: Synergizing Reasoning and Acting in Language Models

Shunyu Yao (Princeton), Jeffrey Zhao (Google Brain), Dian Yu (Google Brain)

Abstract

We explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner. ReAct allows LLMs to interact with external tools to retrieve additional information, leading to more reliable and factual responses.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

ReAct is the foundational paper for tool-using agents. Every enterprise agent framework today builds on this pattern. The key insight — that reasoning and acting must be interleaved, not sequential — is still underappreciated in production deployments.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Key Contributions

  • →ReAct framework combining reasoning and acting
  • →Interleaved thought-action-observation traces
  • →Demonstrated on HotpotQA and Fever

Topics

reasoningtool useagent planninglong-horizon agents