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 expert 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 agent settings. EvoAgent can be generalized to any LLM-based agent framework, and can automatically extend the existing agent framework to multi-agent systems without any extra human designs. Experimental results across various tasks have shown that EvoAgent can automatically generate multiple expert agents and significantly enhance the task-solving capabilities of LLM-based agents.

翻译：强大大型语言模型（LLMs）的兴起推动了基于LLM的自主智能体构建新趋势，尤其是在多智能体系统领域。尽管取得了显著进展，我们注意到现有研究严重依赖人工设计的框架，这极大限制了智能体系统的功能范围与可扩展性。如何将专用智能体自动扩展为多智能体系统以提升任务解决能力，仍然是一个重大挑战。本文提出EvoAgent——一种通过进化算法将专家智能体自动扩展为多智能体系统的通用方法，从而提升基于LLM的智能体在任务解决中的效能。具体而言，我们将现有智能体框架视为初始个体，通过应用系列进化算子（如变异、交叉、选择等）生成具有多样化智能体配置的多个智能体。EvoAgent可泛化至任何基于LLM的智能体框架，且无需额外人工设计即可将现有智能体框架自动扩展为多智能体系统。多任务实验结果表明，EvoAgent能自动生成多个专家智能体，并显著增强基于LLM的智能体的任务解决能力。