paperAugust 2026Unreviewed

Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systems

I. Shraga, Roei Eshel, Lior Gorelik

Abstract

A large language model (LLM) guardrail for a self-adaptive system (SAS) may issue an approval that is correct at check time but stale by actuation. This creates an Execute-stage time-of-check to time-of-use (TOCTOU) hazard. We study verdict freshness: whether a guardrail verdict remains valid when used. We distinguish three quantities that answer different questions: all-candidate verdict change under fixed-action replay, oracle-labeled approval expiry on recorded closed-loop trajectories, and j

Cite

@misc{shraga2026approved,
  title = {{Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systems}},
  author = {I. Shraga and Roei Eshel and Lior Gorelik},
  year = {2026},
  month = aug,
  eprint = {2608.26306},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/a2e0b37b50504ec982323457953492e9a489cd55}
}