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

2026-09-14

AI Summary

为解决多智能体系统中记忆机制易受噪声影响及差异性丧失的问题，提出CoMem架构，通过个体与集体记忆协同提升学习效果。

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 diversity.Experiments on ALFWorld and PDDL benchmarks show that CoMem achieves strong overall performance and robustly avoids memory pollution.

Problem

• memory mechanisms
• multi-agent systems
• noise
• agent differences

Innovation

• Collective-Individual Memory Synergy
• Private Experience Sedimentation
• Collective Wisdom Curation
• Parallel Dual-Stream Retrieval