Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems

• URL: http://arxiv.org/abs/2604.19540v1
• Date: Tue, 21 Apr 2026 15:00:25 GMT
• Title: Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems
• Abstract summary: LLM agents increasingly collaborate on tasks spanning days or weeks.<n>This requires agents to share, evaluate, and combine each other's cognitive state in real time across sessions.<n>We call this cross-session agent-to-agent cognitive collaboration, distinct from parallel agent execution.
• Score: 0.9494375075678443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Teams of LLM agents increasingly collaborate on tasks spanning days or weeks: multi-day data-generation sprints where generator, reviewer, and auditor agents coordinate in real time on overlapping batches; specialists carrying findings forward across session restarts; product decisions compounding over many review rounds. This requires agents to share, evaluate, and combine each other's cognitive state in real time across sessions. We call this cross-session agent-to-agent cognitive collaboration, distinct from parallel agent execution. To enable it, three problems must be solved together. (P1) Each agent decides field by field what to accept from peers, not accept or reject whole messages. (P2) Every claim is traceable to source, so returning claims are recognised as echoes of the receiver's own prior thinking. (P3) Memory that survives session restarts is relevant because of how it was stored, not how it is retrieved. These are protocol-level properties at the semantic layer of agent communication, distinct from tool-access and task-delegation protocols at lower layers. We call this missing protocol layer "semantic infrastructure," and the Mesh Memory Protocol (MMP) specifies it. Four composable primitives work together: CAT7, a fixed seven-field schema for every Cognitive Memory Block (CMB); SVAF, which evaluates each field against the receiver's role-indexed anchors and realises P1; inter-agent lineage, carried as parents and ancestors of content-hash keys and realising P2; and remix, which stores only the receiver's own role-evaluated understanding of each accepted CMB, never the raw peer signal, realising P3. MMP is specified, shipped, and running in production across three reference deployments, where each session runs an autonomous agent as a mesh peer with its own identity and memory, collaborating with other agents across the network for collective intelligence.

Related papers

• A Technical Taxonomy of LLM Agent Communication Protocols [60.76747983053368]
  This study develops a technical taxonomy to classify and analyze large language models (LLMs) agent communication protocols.<n>The framework guides protocol selection and highlights open research gaps such as privacy and policy enforcement.
  arXiv  Detail & Related papers  (2026-06-17T14:45:20Z)
• MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation [11.486913474115402]
  We propose MetaCogAgent, a multi-agent large language model (LLM) framework where each agent is equipped with a Metacognitive Self-Assessment Unit.<n>We show that MetaCogAgent achieves 82.4% task accuracy while using 5% fewer API calls than AutoGen and 34% fewer than ensemble voting.
  arXiv  Detail & Related papers  (2026-05-17T07:12:04Z)
• MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration [2.643905034529239]
  MPAC is an application-layer protocol that fills this gap with explicit coordination semantics across five layers.<n> specification defines 21 message types, three state machines with normative transition tables, Lamport-clock causal watermarking, two execution models, three security profiles, and optimistic control on shared state.<n>A controlled three-agent code review benchmark shows a 95 percent reduction in coordination overhead and a 4.8 times wall-clock speedup.
  arXiv  Detail & Related papers  (2026-04-10T01:12:05Z)
• Co-TAP: Three-Layer Agent Interaction Protocol Technical Report [25.250986874331645]
  Co-TAP is a three-layer agent interaction protocol designed to address the challenges faced by multi-agent systems.<n>We have designed and proposed a layered solution composed of three core protocols: the Human-Agent Interaction Protocol (HAI), the Unified Agent Protocol (UAP), and the Memory-Extraction-Knowledge Protocol (MEK)
  arXiv  Detail & Related papers  (2025-10-09T14:20:19Z)
• SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents [0.0]
  SAMEP (Secure Agent Memory Exchange Protocol) is a novel framework that enables persistent, secure, and semantically searchable memory sharing among AI agents.<n>Our protocol addresses three critical challenges: (1) persistent context preservation across agent sessions, (2) secure multi-agent collaboration with fine-grained access control, and (3) efficient semantic discovery of relevant historical context.
  arXiv  Detail & Related papers  (2025-07-05T02:20:09Z)
• PBFT-Backed Semantic Voting for Multi-Agent Memory Pruning [0.0]
  This paper introduces the Co-Forgetting Protocol to enable synchronized memory pruning in multi-agent systems (MAS)<n>The protocol integrates three key components: (1) context-aware voting, where agents utilize a lightweight DistilBERT model to assess the relevance of memory items based on their content and the current operational context; (2) multi-scale temporal decay functions, which assign diminishing importance to memories based on their age and access frequency across different time horizons; and (3) a Practical Byzantine Fault Tolerance (PBFT)-based consensus mechanism, ensuring that decisions to retain or discard memory items are agreed upon by a qualified and fault-tolerant majority of agents
  arXiv  Detail & Related papers  (2025-06-19T08:28:29Z)
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
  We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
  arXiv  Detail & Related papers  (2025-06-18T19:44:46Z)
• PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC [98.82146219495792]
  In this paper, we propose a hierarchical agent framework named PC-Agent.<n>From the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content.<n>From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture.
  arXiv  Detail & Related papers  (2025-02-20T05:41:55Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [67.76186488361685]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency [65.28061634546577]
  Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem. In this paper, we propose bidirectional action-dependent Q-learning (ACE) ACE outperforms the state-of-the-art algorithms on Google Research Football and StarCraft Multi-Agent Challenge.
  arXiv  Detail & Related papers  (2022-11-29T10:22:55Z)
• Learning From Good Trajectories in Offline Multi-Agent Reinforcement Learning [98.07495732562654]
  offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets. One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team. We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
  arXiv  Detail & Related papers  (2022-11-28T18:11:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.