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

arXiv: https://arxiv.org/abs/2603.10062 · HTML: https://mlsanity.com/paper/2603.10062/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 9 of 9)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving](https://mlsanity.com/paper/2411.02820/) (2024)

## Built on by (most cited first, 9 of 9)

- [MemTX: Transactional Belief Commit for Stateful Agent Memory](https://mlsanity.com/paper/2607.23929/) (2026)
- [Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents](https://mlsanity.com/paper/2606.22504/) (2026)
- [Token Economics for LLM Agents: A Dual-View Study from Computing and Economics](https://mlsanity.com/paper/2605.09104/) (2026)
- [Self-Evolving Multi-Agent Systems via Decentralized Memory](https://mlsanity.com/paper/2605.22721/) (2026)
- [Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems](https://mlsanity.com/paper/2610.08101/) (2026)
- [Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems](https://mlsanity.com/paper/2604.19540/) (2026)
- [Rosetta Memory: Adaptive Memory for Cross-LLM Agents](https://mlsanity.com/paper/2606.07711/) (2026)
- [Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory](https://mlsanity.com/paper/2609.03340/) (2026)
- [Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models](https://mlsanity.com/paper/2610.16165/) (2026)

## Abstract (arXiv)

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.