---
id: "yao-react"
title: "ReAct: Synergizing Reasoning and Acting in Language Models"
creator: "Shunyu Yao et al."
creator_url: "https://arxiv.org/abs/2210.03629"
url: "https://arxiv.org/abs/2210.03629"
level: "advanced"
level_max: null
category: "agents"
subcategory: "agent-design-patterns"
region: "West"
license: "open"
license_scope: "linked-resource"
models: ["any"]
source_date: "2022-10-06"
date_added: "2026-10-18"
---

[Agents and harnesses](/agents/index.md)

# ReAct: Synergizing Reasoning and Acting in Language Models

by [Shunyu Yao et al.](https://arxiv.org/abs/2210.03629)

[Read the original →](https://arxiv.org/abs/2210.03629)

Research on combining reasoning with environment actions, a useful reference for agent-loop design.

The paper investigates alternating model reasoning with actions in an environment. It provides research context for agent loops; reproducing results requires implementing and evaluating the surrounding system.

Level: [Advanced](/levels/index.md#advanced)
Models: any
Category: [Agents and harnesses](/agents/index.md)
Tags: [research](/tags/research/index.md), [design-patterns](/tags/design-patterns/index.md)
Source date: 2022-10-06
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok
Prerequisites: Requires implementation experience or critical reading of technical methods and system trade-offs.
Subcategory: [agent design patterns](/agents/agent-design-patterns/index.md)
Region: West
Original language: en
Access: free
Resource reuse: open: Source states by/4.0. Applies to the linked resource, not every referenced model or dataset. [Facet definitions](/about/index.md#facets)

Summary in our own words. Rights remain with the original creator. [Credit and correction policy](/about/index.md#credit-policy).

[Plain-text Markdown copy](/agents/agent-design-patterns/yao-react/index.md)