Shared selective persistent memory lifts agent task completion to 96%, while storing full history drops it to 71%
Apple's ML research team self-reports that an agent LLM system keeping only four reusable context types reaches 96% task completion, versus 79% with no memory and 71% with full history.
ImportanceLocalEvidenceE2 unreplicated
An agent LLM system using shared selective persistent memory reached 96% task completion across three enterprise deployment scenarios, compared with 79% with no memory and 71% when persisting the full history — results published by Apple's machine learning research team on September 16.
The prior approaches were persisting the full history or using no memory at all; the former actually hurt task completion, and session-level reasoning traces consume substantial context.
The method keeps only four reusable context types — task specifications, data schemas, tool configurations, and output constraints — discards session-level reasoning traces, and supports cross-user sharing. The team self-reports that summary-driven data representation cuts token cost by roughly 97x versus injecting raw data. All figures are vendor self-reported.
Boundary: results are limited to three enterprise deployment scenarios and no third-party replication yet; the preprint was submitted to arXiv on July 10 (arXiv:2607.09493) and updated to v2 on September 15.