Skytliang/Multi-Agents-Debate

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

49
/ 100
Emerging

This project helps people get more accurate answers from Large Language Models (LLMs) by simulating a debate. Instead of a single LLM trying to solve a problem on its own, two LLMs (a 'devil' and an 'angel') argue and correct each other's biases, with a third LLM acting as a judge. This process refines initial outputs, leading to more robust and less 'biased' results, particularly for complex reasoning or translation tasks. It's for anyone using LLMs for critical tasks who needs to minimize errors from a single LLM's 'thinking'.

532 stars.

Use this if you need to improve the reliability and accuracy of answers generated by Large Language Models, especially for tasks requiring nuanced reasoning or translation where a single model might produce biased or incomplete responses.

Not ideal if you need instant, simple answers where the overhead of a multi-agent debate isn't justified, or if you are working with extremely short, factual queries.

AI-powered-reasoning natural-language-processing complex-problem-solving AI-content-validation translation-quality-improvement
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

532

Forks

57

Language

Python

License

GPL-3.0

Category

ai-debate-arenas

Last pushed

Dec 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Skytliang/Multi-Agents-Debate"

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