CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems

Abstract:Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better over time. While recent work has led to strong cooperation skills, most methods still use flat, unstructured memories, which easily get filled with noise and erase differences between agents. To address this, we introduce the concept of collective-individual memory synergy and propose CoMem, an architecture that unifies both private experience and shared knowledge for multi-agent learning. CoMem features:(i) Private Experience Sedimentation, which lets each agent keep and update its own useful memories over time;(ii) Collective Wisdom Curation, which carefully selects only widely proven ideas to be shared among agents;(iii)Parallel Dual-Stream Retrieval, which allows agents to draw both from their own memory and the group's wisdom, using clustering to ensure this http URL on ALFWorld and PDDL benchmarks show that CoMem achieves strong overall performance and robustly avoids memory pollution.

Submitted to AAAI 2027.9 pages,4 figures

Artificial Intelligence (cs.AI)

arXiv:2609.15009 [cs.AI]

(or arXiv:2609.15009v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.15009 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.