arXiv (All)
open access
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle#1052129
- Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory#1233047
- Hallucination, Agency Illusions, and Safety Failures in Language Models A Constraint-Based Account of Stateless Reasoning#71642
- Embodied Episodic Memory: a New Case for Causalism?#760008
- Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy#1216778
Record · ID 1248115
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive