MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs

TL;DR

MegaAgent introduces a scalable, autonomous multi-agent system powered by large language models that dynamically generates agents and tasks without relying on predefined procedures, significantly improving efficiency and scalability.

Contribution

It presents MegaAgent, a novel large-scale LLM-based multi-agent system that autonomously generates agents and manages tasks without predefined SOPs, enhancing scalability and flexibility.

Findings

Successfully developed a Gobang game in 800 seconds

Scaled up to 590 agents in a policy simulation

Outperformed existing systems like MetaGPT in efficiency

Abstract

LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptional performance, successfully developing a Gobang game within 800 seconds and scaling up to 590 agents in a national policy simulation to generate multi-domain policies. It significantly outperforms existing systems, such as MetaGPT, in both task completion efficiency and scalability. By eliminating the need for predefined SOPs, MegaAgent demonstrates exceptional scalability and autonomy, setting a foundation for advancing true autonomy in MAS. Our code is available at https://github.com/Xtra-Computing/MegaAgent .