ReAct logo

ReAct

ysymyth/ReAct

ReAct Prompting for decision-making with language models

GraphCanon updated 3d · GitHub synced 3d · 32 views this month

4.1k stars396 forksLast push 2y Jupyter Notebook MIT

Decision brief

ReAct enhances large language models by improving reasoning and executing actions through specific tasks using GPT-3.

Good fit when

  • When aiming for better decision-making in HotpotQA, alfworld environments, or WebShop scenarios with GPT-3
  • For projects that benefit from detailed action-reasoning sequences as seen in AlfWorld success rates

Avoid when

  • If requiring extensive custom task integration beyond provided notebooks, LangChain's zero-shot ReAct agent may be more preferable
  • When PaLM outperforms GPT-3 on specific tasks or if an alternative model is preferred

Observed Jul 14, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Dormant (923d since push)
As of 3d
Provenance
Not a fork · Personal account
As of 3d
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/ysymyth/ReAct

How it fits your stack(4)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A repository containing GPT-3 prompting code for the ReAct method that enhances reasoning and action in large language models through specified tasks such as HotpotQA, FEVER, AlfWorld, and WebShop.

Capability facts

Languages
jupyter notebook

Source: github.language · Aug 17, 2026

Categories

Graph entities

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

LangChain integrationLangChain

Source: README excerpt (regex_v1, Aug 17, 2026)

To use ReAct for more tasks, consider trying [LangChain's zero-shot ReAct Agent](https://python.langchain.com/docs/modules/agents/agent
Source link
OpenAI APIOpenAI API

Source: README excerpt (regex_v1, Aug 17, 2026)

You need to first have an OpenAI API key and store it in the environment variable ``OPENAI_API_KEY`` (see [here](htt
Source link
Python runtimePython

Source: README excerpt (regex_v1, Aug 17, 2026)

Act for more tasks, consider trying [LangChain's zero-shot ReAct Agent](https://python.langchain.com/docs/modules/agents/agent_types/react.html).
Source link

Tags

README

ReAct Prompting

GPT-3 prompting code for ICLR 2023 paper ReAct: Synergizing Reasoning and Acting in Language Models.

To use ReAct for more tasks, consider trying LangChain's zero-shot ReAct Agent.

Setup

You need to first have an OpenAI API key and store it in the environment variable OPENAI_API_KEY (see here).

Package requirement: openai, and install alfworld following instructions here.

Experiments

Run {hotpotqa,fever,alfworld,webshop}.ipynb. As HotpotQA and FEVER have large validation sets, we only run 500 random examples (see notebooks). We find PaLM and GPT-3 are better at different tasks.

HotpotQA (500 random dev, EM)FEVER (500 random dev, EM)AlfWorld (success rate)WebShop (success rate)
PaLM-540B (paper)29.462.270.940
GPT-3 (davinci-002)30.45478.435.8

Citation

@inproceedings{yao2023react,
  title = {{ReAct}: Synergizing Reasoning and Acting in Language Models},
  author = {Yao, Shunyu and Zhao, Jeffrey and Yu, Dian and Du, Nan and Shafran, Izhak and Narasimhan, Karthik and Cao, Yuan},
  booktitle = {International Conference on Learning Representations (ICLR) },
  year = {2023},
  html = {https://arxiv.org/abs/2210.03629},
}

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.