ysymyth/ReAct

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

46
/ 100
Emerging

This is a prompting strategy for large language models like GPT-3 that helps them tackle complex questions or perform actions in digital environments. It takes a prompt and enables the model to reason through steps and interact with tools to produce more accurate answers or complete tasks. This is for AI researchers or developers building intelligent agents who want to improve their language models' ability to solve problems by combining logical thought with external actions.

3,629 stars. No commits in the last 6 months.

Use this if you are a researcher or developer working with large language models and want to enhance their performance on tasks requiring multi-step reasoning and interaction with external environments, like question answering or automated online shopping.

Not ideal if you are an end-user looking for a ready-to-use application; this is a research-oriented codebase for exploring prompting techniques, not a production tool.

AI-research language-model-prompting intelligent-agents natural-language-processing reasoning-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

3,629

Forks

356

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ysymyth/ReAct"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.