SOURCE-LINKED INTELLIGENCE

The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adversarial. The cost of implementing a defense is paid with each interaction, while its benefits are only seen in a small percentage of cases. We developed a measurement setup that keeps the memory backend, retrieval process, and judge consistent across different conditions, changing only the defense itself. We test each condition three times across five conversations to distinguish the defense's real effects from noise inherent in the pipeline's ru

Read original source ↗ Open in workspace

recordType

paper

region

Global