AI agents2 min read
What to Admit and How to Present: Governing Persistent Memory in LLM Agents
Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decisions: admission, which determines what recalled information enters the working context, and presentation, which determines how admitted information…
By Chang Liu, Deliang DingarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 9, 2026.
Comments
Sign in to join the discussion.