LatentMem: 为多智能体系统定制潜在记忆
LatentMem: Customizing Latent Memory for Multi-Agent Systems
AI总结：
LatentMem通过定制智能体特定的记忆和优化策略，提升了多智能体系统的性能表现。
摘要：
大型语言模型（LLM）驱动的多智能体系统（MAS）展示了显著的集体智能，其中多智能体记忆是持续适应的关键机制。然而，现有的多智能体记忆设计仍然受到两个根本瓶颈的限制：（i）由于缺乏角色感知的定制，导致记忆同质化；（ii）由于记忆条目过于细粒度，导致信息过载。为了解决这些限制，我们提出了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特定的记忆。具体而言，LatentMem包含一个经验银行，用于以轻量形式存储原始交互轨迹，以及一个记忆合成器，该合成器根据检索到的经验和智能体特定的上下文合成紧凑的潜在记忆。进一步，我们引入了潜在记忆策略优化（LMPO），它通过潜在记忆将任务级优化信号传递到合成器，鼓励其生成紧凑且高用途的表示。在多样化的基准和主流MAS框架上的广泛实验表明，LatentMem在 vanilla 设置上实现了高达19.36%的性能提升，并且在不修改底层框架的情况下，始终优于现有记忆架构。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
