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.

翻译：基于大语言模型（LLM）的多智能体系统（MAS）展现出卓越的集体智能，其中多智能体记忆作为持续适应的关键机制。然而，现有多智能体记忆设计仍受限于两个基本瓶颈：（i）因缺乏角色感知定制而导致的内存同质化；（ii）因记忆条目过度细粒度而引起的信息过载。为克服这些局限，我们提出LatentMem——一种可学习的多智能体记忆框架，旨在以令牌高效的方式定制智能体专属记忆。具体而言，LatentMem包含以轻量化形式存储原始交互轨迹的经验库，以及根据检索到的经验与智能体特定上下文合成紧凑潜在记忆的记忆组合器。进一步，我们提出潜在记忆策略优化（LMPO），该方法通过潜在记忆将任务级优化信号传递至组合器，促使其生成紧凑且高效用的表征。在多样化基准测试与主流MAS框架上的大量实验表明，LatentMem相比原始设置最高可获得$19.36$%的性能提升，且无需对底层框架进行任何修改即可持续优于现有记忆架构。