Shared Selective Persistent Memory for Agentic LLM Systems

Summary

Agentic LLM systems that generate code through multi-turn tool use lose configuration choices, domain constraints, schemas, and tool-use patterns when each session starts from zero. The proposed shared selective persistent memory retains task specifications, data schemas, tool configurations, and output constraints while discarding session-specific reasoning traces, and allows workspaces to be transferred across users with role-based access control. In a deployed collaborative workspace platform, agents create and maintain git-versioned dashboards, reports, and data-driven documents from CSV, SQL, REST API, and MCP sources; draft isolation supports risk-free changes and restoration without re-invoking the model. Results across three enterprise scenarios show 96% task completion, compared with 79% without memory and 71% with full history, while zero-token refresh cut recurring-update task time 14× and summary-driven generation reduced token cost 97× versus raw data injection.

Takeaways

1. 1

   Selective memory achieved 96% task completion across three enterprise deployment scenarios, versus 79% without memory and 71% with full-history persistence.

2. 2

   Full-history persistence can reduce performance because stale reasoning traces bias the agent; selective memory outperformed both no-memory and full-history approaches.

3. 3

   Zero-token data refresh succeeded in 12/12 public-dataset trials, while summary-driven generation reduced per-invocation token cost by 97× versus raw data injection.

FAQ