AI 中文总结
针对AI智能体跨会话失忆问题，提出将记忆作为可插拔中间件层，通过六个系统挑战构建参考实现ALTK-Evolve，实现自我改进。
AI 中文摘要
AI智能体在默认情况下跨会话是无状态的，因此在操作上是失忆的：每个会话开始时几乎没有关于先前失败、修复、偏好或成功策略的持久知识。结果，智能体重复相同的错误，并丢弃来之不易的经验。主要的解决方法是定制记忆——检索、持久化和学习逻辑被手工编织进单个智能体，并绑定到单个存储引擎。这造成了一个碎片化的格局，其中记忆无法独立于拥有它的智能体而被交换、共享、隔离或推理。我们认为这是一个中间件问题：智能体记忆应获得一流的、可插拔的层，正如数据访问、消息传递和持久化各自成为中间件关注点一样。我们通过六个系统挑战来发展这一愿景：双面可插拔性、宿主原生介入、多租户隔离、写路径一致性、带来源的联邦共享以及生命周期治理。我们提出了ALTK-Evolve，一个用于自我改进智能体的记忆中间件的参考实现，并用它来推动未来记忆中间件的更广泛研究议程。
英文摘要
AI agents are stateless across sessions by default and therefore operationally amnesic: each session begins with little durable knowledge of prior failures, repairs, preferences, or successful strategies. As a result, agents repeat the same mistakes and discard hard-won experience. The dominant fix is \emph{bespoke memory}---retrieval, persistence, and learning logic hand-wired into one agent and bound to one storage engine. This creates a fragmented landscape where memory cannot be swapped, shared, isolated, or reasoned about independently of the agent that owns it. We argue that this is a middleware problem: agent memory deserves a first-class, pluggable layer, just as data access, messaging, and persistence each became middleware concerns. We develop this vision through six systems challenges: two-sided pluggability, host-native interposition, multi-tenant isolation, write-path consistency, federated sharing with provenance, and lifecycle governance. We present ALTK-Evolve, a reference implementation of memory middleware for self-improving agents, and use it to motivate a broader research agenda for future memory middleware.
CommentsConditionally accepted to Middleware 2026. Extended version
