Shared Selective Persistent Memory Lifts Agentic Task Completion to 96% and Cuts Per-Call Token Cost 97x

arXiv·high signal

This method retains four categories of reusable context — task specifications, data schemas, tool configurations, and output constraints — while discarding session-specific reasoning, enabling role-based workspace transfer across users. It reports 96% task completion versus 79% without memory, a 14x faster 'zero-token' data refresh for recurring updates, and 97x lower per-invocation token cost versus injecting raw data each time. A concrete blueprint for builders wiring persistent memory into multi-agent LLM systems.