# Apple — Shared Selective Persistent Memory for Agentic LLM Systems

- Company: Apple (apple.com)
- Announced: 2026-09-16
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://machinelearning.apple.com/research/shared-selective-persistent-memory
- Record: https://forck.live/items/11410-shared-selective-persistent-memory-for-agentic-llm-systems
- Subject: Machine Learning Research

Apple researchers introduce shared selective persistent memory, a memory architecture for agentic LLM systems that identifies and retains four categories of reusable context—task specifications, data schemas, tool configurations, and output constraints—while discarding session-specific reasoning traces. The architecture is implemented in a deployed collaborative workspace platform where LLM agents produce, edit, and maintain git-versioned artifacts from heterogeneous data sources. Across three enterprise deployment scenarios, shared selective persistent memory achieves 96% task completion (vs. 79% without memory and 71% with full history), and a complementary zero-token data refresh mechanism eliminates LLM re-invocation for recurring data updates (14× task time reduction).

## Evidence

Verbatim from https://machinelearning.apple.com/research/shared-selective-persistent-memory:

> We introduce shared selective persistent memory, a memory architecture for agentic systems that identifies and retains four categories of reusable context—task specifications, data schemas, tool configurations, and output constraints—while discarding session-specific reasoning traces.

---

Record: https://forck.live/items/11410-shared-selective-persistent-memory-for-agentic-llm-systems
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md