EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

TL;DR

EvoAgent introduces an evolutionary algorithm-based method to automatically extend single-agent LLM systems into multi-agent systems, significantly enhancing their task-solving capabilities and scalability.

Contribution

The paper presents a novel, generic evolutionary approach to automatically generate multi-agent systems from existing single-agent frameworks, reducing reliance on human design.

Findings

EvoAgent significantly improves task-solving performance across various tasks.

The method generalizes to any LLM-based agent framework.

Experimental results demonstrate enhanced effectiveness of multi-agent systems.

Abstract

The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend specialized agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LLM-based agents in solving tasks. Specifically, we consider the existing agent frameworks as the initial individual and then apply a series of evolutionary operators (e.g., mutation, crossover, selection, etc.) to generate multiple agents with diverse settings. Experimental results across various tasks show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents, and can be generalized to any LLM-based agent framework to extend them into multi-agent systems. Resources are available at https://evo-agent.github.io/.