zjunlp/MachineSoM
[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
This project helps researchers and developers understand how different collaboration strategies, like debate and self-reflection, affect the problem-solving abilities of AI agents. It takes experimental data from AI agent simulations with varying 'personalities' (traits like being easy-going or overconfident) and outputs statistical analyses, performance metrics, and visualizations. Anyone designing, evaluating, or studying multi-agent AI systems could use this.
120 stars. No commits in the last 6 months.
Use this if you are researching how AI agents can collaborate more effectively to tackle complex tasks, and you want to analyze the impact of different social dynamics and interaction strategies on their collective performance.
Not ideal if you are looking for a plug-and-play solution to deploy multi-agent systems for immediate practical applications rather than for research and experimentation.
Stars
120
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jun 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/MachineSoM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...