潜在记忆体：面向多智能体系统的定制化潜在记忆机制

摘要

基于大语言模型的多智能体系统展现出卓越的集体智能，其中多智能体记忆机制是实现持续适应的关键。然而，现有记忆设计仍受两大瓶颈制约：（一）因缺乏角色感知定制而导致的内存同质化；（二）过度细粒度记忆条目引发的信息过载。为此，我们提出LatentMem——一种可学习的多智能体记忆框架，能以令牌高效的方式定制智能体专属记忆。具体而言，LatentMem包含以轻量形式存储原始交互轨迹的经验库，以及根据检索经验和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，我们引入潜在记忆策略优化算法，通过潜在记忆将任务级优化信号传递至组合器，促使其生成紧凑高效的表征。在多样化基准测试和主流多智能体框架上的实验表明，LatentMem相比原始设置最高可获得19.36%的性能提升，且无需修改底层框架即可持续优于现有记忆架构。

English

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.

潜在记忆体：面向多智能体系统的定制化潜在记忆机制

LatentMem: Customizing Latent Memory for Multi-Agent Systems

摘要

Support