提出新型长期智能体记忆架构，解决传统数据库式记忆的四大缺陷。
Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory
- 用状态演进替代记录操作，设计四类全局控制的记忆运算
- 定义六项正确性条件，证明现有系统无法满足
- 构建原型系统MemState，为专用记忆引擎指明研究方向
长期运行的AI智能体需要持久化记忆。现有记忆系统与数据库范式将记忆视为存储，仅在记录、嵌入或边级别保证正确性，难以满足长期记忆需求。结果导致四大失效模式：无约束增长、语义修订缺失、容量驱动遗忘和只读检索。本文提出，长期智能体记忆应作为新的数据管理任务，其正确性取决于状态轨迹而非单个记录。为此提出受控演化记忆（GEM）框架，以摄入、修订、遗忘、检索四类状态级操作替代传统数据库操作，并设立六项正确性条件。三个结构性结论表明，任何基于记录的系统均无法满足这些条件。通过在属性图后端实现的MemState原型验证了可行性，揭示了与原生引擎的差距。最后提出三个研究方向，确立以记忆为中心的数据管理新范式。
原文摘要 · Abstract (English)
Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as storage. They localize correctness at records, embeddings, or edges. Each supplies only some of the capabilities that long-term memory requires. The result is four recurring failure modes: unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval. In our vision, long-term agent memory is a new data-management workload. Its correctness is a property of the state trajectory, not of individual records. We formalize this as Governed Evolving Memory (GEM). GEM replaces record-level database operations with four state-level operators: ingestion, revision, forgetting, and retrieval. Six correctness conditions govern how the state evolves. Three structural observations establish that no record-level system can satisfy these conditions, regardless of the storage model. We realize the abstraction in MemState, a prototype on a property-graph backend. MemState validates feasibility and exposes the gap to a native engine. We outline three research directions that define memory-centric data management as a workload.
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。