arxiv.org/abs/2609.22818 The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents
A study measures the benign-traffic cost of four memory-poisoning defenses for LLM agents, using half of LoCoMo with three repeated runs. The write-time defenses showed no detectable accuracy cost, while the read-time reranker withheld memory from 45% of questions and lowered core accuracy by 4.4 points, a borderline effect.
— via arXiv Cryptography Security, Pritom Bhowmik
