Apple proposes shared selective persistent memory to fix agent LLM context amnesia
Apple ML Research · rss · 2026-09-16
Apple ML Research introduces shared selective persistent memory, a memory architecture for agentic LLM systems that generate code via multi-turn tool use.
- Problem: each session starts from zero, discarding configuration choices, domain constraints, data schemas, and tool-use patterns from previous sessions
- Naively persisting full conversation histories is token-inefficient and actually degrades generation quality due to irrelevant context
- The architecture identifies and retains four categories of reusable context—task specifications, data schemas, and more—shared across sessions
Goal: let later sessions inherit the context that made earlier ones productive, without the noise.
More from coding & agent
- Microsoft's MemSteer turns unlabeled user histories into agent memory supervision — MicrosoftResearch · 2026-11-02
- She fired herself from her own Instagram: AI agent runs the account, views up 82.3% — heyshrutimishra · 2026-11-02
- Sourcegraph: AI writes code faster than teams can review it, driving more outages — AI Engineer · 2026-11-02
- Tsinghua & Microsoft's HarnessMM cuts agent token use by up to 87.93% while raising success rate — rohanpaul_ai · 2026-11-02
- GitHub launches Agent HQ: Anthropic, OpenAI, Google coding agents in Copilot — emmanuelvivier · 2026-11-02
- DeepSeek open-sources Super-Agent, a coding agent that reads team chats to minimize human input — emmanuelvivier · 2026-11-02