AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact is marked invalid and retained rather than deleted. However, whether that mark is enforced at retrieval time is unexamined. In this paper, we measure five such systems: we load each with a revoked policy and its replacement, track whether the revoked fact is returned at retrieval and whether the agent then acts on it across nine policy scenarios and nine models, and score every trial under six defense conditions. We find that no system enforces

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T20:22:01.598Z. This is not the publication date.