REPOGEO REPORT · LITE

Skytliang/Multi-Agents-Debate

Default branch main · commit e58d1460 · scanned 6/10/2026, 1:23:00 PM

GitHub: 579 stars · 63 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE

33 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

2 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface Skytliang/Multi-Agents-Debate, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

hightopics#1

Add more specific topics to improve category visibility

Why:

CURRENT

chatgpt, gpt-4, large-language-models, llms, nlp

COPY-PASTE FIX

chatgpt, gpt-4, large-language-models, llms, nlp, multi-agent-systems, llm-agents, debate-framework, agent-frameworks, reasoning

highreadme#2

Reposition README opening to highlight framework nature

Why:

CURRENT

:fire:This work aims to explore the debating capability of LLMs by proposing the **MAD** framework, which stands for **M**ultiA**gents **D**ebate.

COPY-PASTE FIX

:fire:MAD is a novel **framework** for exploring and enabling the debating capability of LLMs, standing for **M**ultiA**gents **D**ebate. It provides a system to simulate adversarial debates among multiple AI agents to improve reasoning and reduce bias.

mediumabout#3

Refine the 'About' description to emphasize 'framework'

Why:

CURRENT

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

COPY-PASTE FIX

MAD: A multi-agent debate framework for Large Language Models, designed to explore and enhance LLM reasoning and reduce bias through adversarial interaction. :D

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface Skytliang/Multi-Agents-Debate

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

microsoft/autogen

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

microsoft/autogen · recommended 1×
joaomdmoura/crewai · recommended 1×
langchain-ai/langchain · recommended 1×
run-llama/llama_index · recommended 1×
OpenAI Function Calling · recommended 1×

CATEGORY QUERY
How can I improve large language model reasoning and reduce bias using multi-agent interaction?
you: not recommended
AI recommended (in order):
1. AutoGen (microsoft/autogen)
2. CrewAI (joaomdmoura/crewai)
3. LangChain Agents (langchain-ai/langchain)
4. LlamaIndex Agents (run-llama/llama_index)
5. OpenAI Function Calling
6. Haystack Agents (deepset-ai/haystack)
AI recommended 6 alternatives but never named Skytliang/Multi-Agents-Debate. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are frameworks for enabling multiple LLMs to debate and refine their generated outputs?
you: not recommended
AI recommended (in order):
1. AutoGen
2. LangChain
3. CrewAI
4. MetaGPT
5. DSPy
AI recommended 5 alternatives but never named Skytliang/Multi-Agents-Debate. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of Skytliang/Multi-Agents-Debate?
pass
AI named Skytliang/Multi-Agents-Debate explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts Skytliang/Multi-Agents-Debate in production, what risks or prerequisites should they evaluate first?
pass
AI named Skytliang/Multi-Agents-Debate explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo Skytliang/Multi-Agents-Debate solve, and who is the primary audience?
pass
AI did not name Skytliang/Multi-Agents-Debate — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of Skytliang/Multi-Agents-Debate. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/Skytliang/Multi-Agents-Debate.svg)](https://repogeo.com/en/r/Skytliang/Multi-Agents-Debate)

HTML

<a href="https://repogeo.com/en/r/Skytliang/Multi-Agents-Debate"><img src="https://repogeo.com/badge/Skytliang/Multi-Agents-Debate.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

Skytliang/Multi-Agents-Debate — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite