Shared Selective Persistent Memory for Agentic LLM Systems

What moved

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…

Why it matters

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… That is a public launch file from Apple, dated 2026-09-16. Tagged LLM / Agents.

On the record

• Filed from the Apple official RSS on 2026-09-16.
• Primary source host: machinelearning.apple.com.
• The desk does not add a second source.