mlsanityData to 7 Oct 2026

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

arXiv 2603.10062 ↗First posted 9 Mar 2026cs.AR cs.AI cs.MAcited by 7

On the map: LLM agents and tool use → Agent memory systems

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.

Key facts. Cited by 7 papers in the map (data through 7 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.

Builds on

9 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025A-MEM: Agentic Memory for LLM Agents17 Feb

Other references · 8

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  3. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  4. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  5. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  8. 2024DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Servingcited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026MemTX: Transactional Belief Commit for Stateful Agent Memorycited by 12
  2. 2026Self-Evolving Multi-Agent Systems via Decentralized Memorycited by 6
  3. 2026Token Economics for LLM Agents: A Dual-View Study from Computing and Economicscited by 5
  4. 2026Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agentscited by 5
  5. 2026Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systemscited by 1
  6. 2026Rosetta Memory: Adaptive Memory for Cross-LLM Agentscited by 0
  7. 2026Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memorycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
  2. 2026Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
  3. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
  4. 2026Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
  5. 2026Are We Ready For An Agent-Native Memory System?
  6. 2026Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
  7. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
  8. 2026Memory as Middleware for Self-Improving AI Agents