Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead

TL;DR

This position paper frames multi-agent memory as a computer architecture problem, distinguishes shared and distributed memory paradigms, proposes a three-layer memory hierarchy, and identifies two critical protocol gaps.

Abstract

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.

Figures (3)

• Figure 1: Two fundamental multi-agent memory architectures for managing growing context complexity: shared memory and distributed memory.
• Figure 2: Agent memory hierarchy and protocol framing.
• Figure 3: Consistency model comparison from traditional memory architecture to multi-agent memory.