为持续学习智能体设计可修正、可演化的记忆系统，避免重复计算历史。
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
- 用带版本的胶囊统一存储语义、来源、有效性与运行状态。
- 支持并发安全的失效机制，降低首令牌延迟并提升重用率。
- 适合构建长期运行的智能体系统，尤其关注记忆可修正性。
持续学习智能体不仅需要更大的上下文窗口和更优的检索能力，还需能持久化、演化并可修正的记忆机制，而不必在每次交互中重新计算历史，或悄然复用过时的运行状态。本文提出PLACEMEM，作为面向持续学习智能体记忆的系统性方案，并实现了一个可执行的控制平面原型。核心主张是：智能体记忆应以带版本的胶囊形式存在，统一语义、溯源、有效性及可重用的运行时状态，形成具备修正感知的身份。当前原型中，胶囊驱动提示级文本检索、基于键值的路由以及对实时后端的级联失效；未来层边界重放虽被明确列为深度集成目标，但暂未作为功能特性声明。原型基于vLLM设计，支持持久胶囊状态、并发安全失效、兼容OpenAI的路由侧车、类型化元数据契约，并配备基准测试工具，可测量首令牌延迟、重用率及修正后行为。该工作既提供了一个展示修正感知控制平面行为的可执行成果，也为未来持续学习系统中的重放感知服务集成提供了具体路线图。
原文摘要 · Abstract (English)
Lifelong agents need more than larger context windows and better retrieval. They need memories that can persist, evolve, and be corrected without forcing the serving stack to recompute the same history on every turn or silently reuse stale runtime state. We present PLACEMEM as a systems position on lifelong-agent memory, instantiated by an executable control-plane prototype. The central claim is that agent memory should be represented as versioned capsules that unify semantics, provenance, validity, and reusable runtime state under one correction-aware identity. In the current prototype, capsules drive prompt-level text retrieval, KV-aware routing, and cascading invalidation over live streamed backends; prospective layer-frontier replay is intentionally framed as a deeper integration agenda rather than a claimed engine feature. We describe a vLLM-first prototype with persistent capsule state, concurrency-safe invalidation, an OpenAI-compatible routing sidecar, a typed metadata contract, and a benchmark harness that measures live first-token latency, reuse, and post-correction behavior. The result is both an executable artifact that demonstrates correction-aware control-plane behavior today and a concrete roadmap for replay-aware serving integration in future lifelong-agent systems.
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。