现有智能体记忆只是查找，无法真正学习与推理。
Contextual Agentic Memory is a Memo, Not True Memory
- 用相似性检索替代规则抽象，本质是查表而非记忆
- 无法突破组合新任务的泛化瓶颈，越堆数据越无效
- 适合关注智能体长期能力与安全性的研究者
当前的智能体记忆系统（向量存储、检索增强生成、草稿板和上下文窗口管理）并未实现真正的记忆，而仅实现了查找。我们将这种将查找误认为记忆的行为视为类别错误，并证明其对智能体能力、长期学习与安全性造成可证明的负面影响。检索依赖于与存储案例的相似性进行泛化；而基于权重的记忆则能将抽象规则应用于从未见过的输入。混淆二者导致智能体无限积累笔记却无法形成专长，在组合新颖任务上存在不可逾越的泛化天花板，且无论上下文大小或检索质量如何提升都无法突破。此外，注入内容会持续传播至所有未来会话，构成结构性漏洞。借鉴神经科学中的互补学习系统理论，我们指出生物智能通过快速海马体实例存储与缓慢新皮层权重整合来解决此问题，而当前AI智能体仅实现前半部分。本文形式化了这些局限，回应四种不同观点，并提出共存建议，呼吁系统构建者、评测设计者与记忆研究社区采取行动。
原文摘要 · Abstract (English)
Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security. Retrieval generalizes by similarity to stored cases; weight-based memory generalizes by applying abstract rules to inputs never seen before. Conflating the two produces agents that accumulate notes indefinitely without developing expertise, face a provable generalization ceiling on compositionally novel tasks that no increase in context size or retrieval quality can overcome, and are structurally vulnerable to persistent memory poisoning as injected content propagates across all future sessions. Drawing on Complementary Learning Systems theory from neuroscience, we show that biological intelligence solved this problem by pairing fast hippocampal exemplar storage with slow neocortical weight consolidation, and that current AI agents implement only the first half. We formalize these limitations, address four alternative views, and close with a co-existence proposal and a call to action for system builders, benchmark designers, and the memory community.
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。