satori-reasoning/Satori

[ICML 2025] Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

36
/ 100
Emerging

Satori is a large language model designed to tackle complex reasoning tasks, particularly in mathematics and other challenging analytical domains. It takes a problem as input and provides a reasoned solution, including self-reflection and exploration of alternative strategies. This tool is for researchers and practitioners who need advanced problem-solving capabilities from an AI.

109 stars. No commits in the last 6 months.

Use this if you need an AI model to solve difficult, multi-step reasoning problems and provide transparent thought processes, especially in quantitative or logical fields.

Not ideal if your primary need is for creative writing, simple question answering, or tasks where a direct, unreasoned answer is sufficient.

advanced problem-solving mathematical reasoning logical deduction AI research complex analytics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

109

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jun 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/satori-reasoning/Satori"

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