SOURCE-LINKED INTELLIGENCE

Large Language Models as Falsifiers for Cyber-Physical Systems

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a robustness optimization problem, traditionally tackled with black-box search algorithms. In parallel, large language models (LLMs) have recently emerged as surprisingly effective optimizers when coupled with iterative prompting. In this work, we connect these ideas and introduce LLM-Falsifier, an LLM-based approach that falsifies specifications by minimizing the STL robustness degree. Beyond generic

Read original source ↗ Open in workspace

recordType

paper

region

Global