发表机构
GraphAI（GraphAI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对企业智能体记忆中的信息泄露问题，提出AkasicMEM，通过传递谱系、策略组合与重评估实现授权连续性，并基于AkasicDB统一存储执行。
AI 中文摘要
智能体记忆使企业智能体能够保留工作期间获得的知识，并在任务和智能体之间重用这些知识，将执行经验转化为持久性的组织知识。要实现这一潜力，既需要源-记忆集成（通过该集成，企业源和累积的记忆可以一起使用），也需要记忆治理（通过该治理，共享记忆在其整个生命周期内始终受组织策略约束）。当来自企业源的信息在记忆中持久化时，这些需求会相互作用。随着这些信息在不断变化的委托人和策略下被反复派生和重用，源限制可能会被绕过，从而导致信息泄露。防止此类泄露需要授权连续性，即在源到记忆以及记忆到记忆的派生和重用过程中，源限制始终保持有效。现有方法分别处理这些问题，但未将源-记忆集成、记忆治理和授权连续性作为跨记忆生命周期的组合核心设计目标。我们将受治理企业记忆定义为围绕这一组合范围设计的智能体记忆，并介绍AkasicMEM作为其实现。AkasicMEM通过传递谱系、记忆形成期间的策略组合以及检索期间的策略重新评估来实现授权连续性。它构建于GraphAI的AkasicDB之上，这是一个统一的向量-图-关系数据库，其存储和执行基础使这些机制的底层操作能够被联合优化和执行。
英文摘要
Agent memory enables enterprise agents to retain knowledge acquired during work and reuse it across tasks and agents, turning execution experience into persistent organizational knowledge. Realizing this potential requires both source--memory integration, through which enterprise sources and accumulated memory can be utilized together, and memory governance, through which shared memory remains subject to organizational policies throughout its lifecycle. These requirements interact when information from enterprise sources persists in memory. As this information is repeatedly derived and reused under changing principals and policies, source restrictions may be bypassed, resulting in information leakage. Preventing such leakage requires authorization continuity, under which source restrictions remain effective throughout source-to-memory and memory-to-memory derivation and reuse. Existing approaches address these concerns individually, but do not treat source--memory integration, memory governance, and authorization continuity as combined core design targets across the memory lifecycle. We define Governed Enterprise Memory as agent memory designed around this combined scope and present AkasicMEM as its realization. AkasicMEM realizes authorization continuity through transitive lineage, policy composition during memory formation, and policy re-evaluation during retrieval. It is built on GraphAI's AkasicDB, a unified vector--graph--relational database whose storage and execution substrate enables the underlying operations of these mechanisms to be jointly optimized and executed.
Comments9 pages, 3 figures
