让多个大模型代理跨会话实时协作,共享思维状态。
Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems

- 用七字段结构化记忆块,按字段细粒度接收同伴信息
- 每条主张可追溯来源,避免重复自言自语式对话
- 重启后记忆仍有效,依赖存储方式而非检索方式
多大模型代理团队在持续数天甚至数周的任务中协同工作:生成、评审与审计代理实时处理重叠数据批次;专家将发现传递至后续会话;产品决策历经多轮评审。这要求代理在会话间实时共享、评估并融合彼此认知状态。我们称此为跨会话代理间认知协作,区别于并行执行。需同时解决三问题:(P1) 代理逐字段决定接受或拒绝同行信息,不整条接收;(P2) 每条主张可追溯源头,返回内容能被识别为自身先前思考的回响;(P3) 会话重启后仍存活的记忆,其相关性源于存储方式,而非检索方式。这些是代理通信语义层的协议级特性,有别于工具调用与任务分派等底层协议。我们称缺失的这一层为“语义基础设施”,并提出“网格记忆协议”(MMP)予以规范。四个可组合原语协同实现:CAT7,为每个认知记忆块(CMB)定义固定七字段模板;SVAF,基于接收方角色锚点评估各字段,实现(P1);代理间溯源,通过内容哈希键的父节点与祖先链实现,达成(P2);Remix,仅保存接收方角色评估后的理解,不存原始同伴信号,实现(P3)。MMP已规范制定,并在三个参考部署中上线运行,每个会话以独立身份和记忆的自治代理作为网格节点,跨网络协作形成集体智能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。