让多智能体记忆更个性高效，提升系统整体表现
LatentMem: Customizing Latent Memory for Multi-Agent Systems
- 按角色定制记忆，用轻量编码合成个性化信息
- 在多个基准上性能最高提升19.36%，且无需改框架
- 适合需要高效协作的多智能体系统研究者
大语言模型驱动的多智能体系统展现出卓越的集体智能，其中多智能体记忆是持续适应的关键机制。然而现有设计存在两大瓶颈：（i）缺乏角色感知导致记忆同质化；（ii）细粒度记忆条目引发信息过载。为此，我们提出LatentMem，一种可学习的多智能体记忆框架，实现以令牌高效方式定制智能体特异性记忆。该框架包含一个轻量存储原始交互轨迹的经验库，以及根据检索经验与智能体上下文生成紧凑潜在记忆的记忆组合器。此外，我们引入潜记忆策略优化（LMPO），将任务级优化信号通过潜记忆传递至组合器，促使生成高价值、紧凑的表示。在多种基准和主流多智能体框架上的实验表明，LatentMem相比基线设置性能最高提升19.36%，且始终优于现有记忆架构，无需修改底层框架。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。