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：随着大语言模型智能体演变为协作式多智能体系统，其记忆需求在复杂性上急剧增长。本文以立场论文形式，将多智能体记忆定性为计算机体系结构问题。我们区分了共享与分布式记忆范式，提出三层记忆层次结构（输入输出层、缓存层与主存层），并识别出两个关键协议缺口：跨智能体的缓存共享机制与结构化记忆访问控制。我们认为当前最紧迫的开放性挑战在于多智能体记忆一致性。这一体系结构视角为构建可靠、可扩展的多智能体系统奠定了理论基础。