PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems

2025/06/13 by Yunlai Deng, Deng, Yingfan, Zhou, Anhao +8
Computer Science · Engineering · #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Modular Robots and Swarm Intelligence #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2506.11803

openalex publication_date 2025/06/13 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28

Abstract

Multi-Agent Systems have recently emerged as a promising paradigm for collaborative reasoning and solving complex tasks. However, the design of collaborative learning algorithms in multi-agent systems faces several challenges, including high communication overhead and insufficient agent-level personalization. In this paper, we propose PE-MA (Parameter-Efficient Multi-Agent Co-Evolution), a novel collaboration framework that supports efficient, scalable, and personalized co-evolution in multi-agent systems. In PE-MA, each agent maintains a lightweight personalized adapter to support agent-specific behavior, while a shared adapter is collaboratively optimized across neighboring agents. This design balances global coordination with local adaptation under heterogeneous environments. We achieve an asymptotically optimal convergence rate of O( 1/(NK)^(1/2) ), where N is the number of agents and K the local update steps.

Related

• Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
• Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
• Multi-Agent Evolve: LLM Self-Improve through Co-evolution
• CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution
• Personalized Collaborative Learning with Affinity-Based Variance Reduction