Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs remain constrained by two fundamental bottlenecks: (i) memory homogenization arising from the absence of role-aware customization, and (ii) information overload induced by excessively fine-grained memory entries. To address these limitations, we propose LatentMem, a learnable multi-agent memory framework designed to customize agent-specific memories in a token-efficient manner. Specifically, LatentMem comprises an experience bank that stores raw interaction trajectories in a lightweight form, and a memory composer that synthesizes compact latent memories conditioned on retrieved experience and agent-specific contexts. Further, we introduce Latent Memory Policy Optimization (LMPO), which propagates task-level optimization signals through latent memories to the composer, encouraging it to produce compact and high-utility representations. Extensive experiments across diverse benchmarks and mainstream MAS frameworks show that LatentMem achieves a performance gain of up to 19.36% over vanilla settings and consistently outperforms existing memory architectures, without requiring any modifications to the underlying frameworks.
@article{arxiv.2602.03036,
title = {LatentMem: Customizing Latent Memory for Multi-Agent Systems},
author = {Muxin Fu and Xiangyuan Xue and Yafu Li and Zefeng He and Siyuan Huang and Xiaoye Qu and Yu Cheng and Yang Yang},
journal= {arXiv preprint arXiv:2602.03036},
year = {2026}
}