As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared and distributed memory paradigms, propose a three-layer memory hierarchy (I/O, cache, and memory), and identify two critical protocol gaps: cache sharing across agents and structured memory access control. We argue that the most pressing open challenge is multi-agent memory consistency. Our architectural framing provides a foundation for building reliable, scalable multi-agent systems.

翻译：随着LLM智能体发展为协作式多智能体系统，其记忆需求的复杂性急剧增长。本立场论文将多智能体记忆问题构建为计算机体系结构问题。我们区分了共享内存与分布式内存范式，提出了三层内存层次结构（I/O层、缓存层与内存层），并指出两个关键协议缺口：跨智能体的缓存共享与结构化内存访问控制。我们认为当前最紧迫的开放挑战在于多智能体内存一致性问题。本文的体系结构框架为构建可靠、可扩展的多智能体系统提供了理论基础。