Evolving teams improve multi-agent collaboration for complex tasks
EvoTeam: Multi-Agent Collaboration via Evolving Teams
Artificial Intelligence
Summary
Solving hard problems often requires many computer agents working together well. This paper introduces a new way to improve how these agents team up and collaborate over time. Instead of just refining individual agents, the authors develop a system that evolves entire teams, their roles, and how they communicate based on experience. This helps teams adapt better across different tasks by reusing successful team structures and skills. The authors tested their approach on several benchmarks, showing it works effectively.
What this means in practice
- •For software development teams: Improve collaborative AI systems that coordinate specialized software agents to automate complex programming or debugging tasks.
- •For robotics control teams: Enhance coordination of multiple robots with specialized roles adapting team strategies to diverse environments and tasks.
Authors
Qinuo Cao, Xin He, Dianxuan Fu, Lizhi Zhang, Zhaoqing Xing, Jiapu Wang, Xin Wang, Na Zou, Yi Chang, Qinggang Zhang
Abstract
LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team collaboration. Recent studies have therefore extended evolution to the collaboration level, using collective execution experience to adjust team organization, and inter-agent interactions. Nevertheless, evolving collaboration across heterogeneous tasks remains challenging, as existing approaches often constrain team reorganization within a shared structure and reuse interaction rules across incompatible team contexts. In this paper, we propose EvoTeam, a collaboration-centric evolution framework that jointly evolves team organization, interaction rules, and individual agent skills through execution experience. It maintains a library of reusable teams, selecting or creating agent teams and guiding collaboration through team-specific interaction rules. Collaboration experience accumulates within compatible team contexts, while individual skills remain reusable across teams. Experiments across four benchmarks demonstrate its effectiveness. Our code is available at https://github.com/DEEP-JLU/EvoTeam.