WindyLab/ConsensusLLM-code
Source code of our paper "Multi-Agent Consensus Seeking via Large Language Models".
This project helps researchers and developers understand how multiple AI agents can reach a shared understanding or agreement on a topic using large language models. You input parameters defining the number of agents, debate rounds, and experiment types (like 'scalar' or '2d' debates), and it outputs experiment data, logs, and automatically generated plots or HTML reports. It is ideal for anyone studying multi-agent systems, AI consensus mechanisms, or the behavior of language models in group settings.
No commits in the last 6 months.
Use this if you are a researcher or AI developer investigating multi-agent consensus seeking using large language models and need a framework to run and visualize debate experiments.
Not ideal if you are looking for a ready-to-use application or a tool that doesn't require direct engagement with Python code and AI model APIs.
Stars
44
Forks
11
Language
Python
License
MIT
Category
Last pushed
Aug 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WindyLab/ConsensusLLM-code"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thu-nics/C2C
[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication...
Traffic-Alpha/iLLM-TSC
This repository contains the code for the paper“iLLM-TSC: Integration reinforcement learning and...
Korde-AI/Multi-User-LLM-Agent
Official code for the paper: "Multi-User Large Language Model Agents"
NyanCyanide/PokeLLM-Battle
Turn-based Pokemon battle environment where Large Language Models (LLMs) control Pokémon and...