苹果研究提出共享选择性持久化内存架构
Shared Selective Persistent Memory for Agentic LLM Systems
苹果搞了个新内存架构，专门给能自己用工具的LLM用，能记住有用的东西，不用每次都从零开始，比单纯存对话历史更高效。
苹果研究提出一种内存架构，用于解决多轮工具使用中的上下文问题。该架构能识别并保留四类可复用上下文（任务规格、数据模式、工具使用模式），避免整个对话历史被保存，从而提升生成代码的质量。
Shared Selective Persistent Memory for Agentic LLM Systems
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is both token-inefficient and counterproductive—irrelevant context degrades generation quality. We introduce shared selective persistent memory, a memory architecture for agentic systems that identifies and retains four categories of reusable context—task specifications, data…
