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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Deng, Yingfan, Zhou, Anhao, Yuan, Yuan, Zhang, Xiao, Zou, Yifei, Yu, Dongxiao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909752586403840
author Deng, Yingfan
Zhou, Anhao
Yuan, Yuan
Zhang, Xiao
Zou, Yifei
Yu, Dongxiao
author_facet Deng, Yingfan
Zhou, Anhao
Yuan, Yuan
Zhang, Xiao
Zou, Yifei
Yu, Dongxiao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems
Deng, Yingfan
Zhou, Anhao
Yuan, Yuan
Zhang, Xiao
Zou, Yifei
Yu, Dongxiao
Multiagent Systems
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.
title PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems
topic Multiagent Systems
url https://arxiv.org/abs/2506.11803