Large Language Models as Falsifiers for Cyber-Physical Systems

原文：Large Language Models as Falsifiers for Cyber-Physical Systems

作者：Ali ArjomandBigdeli, Jiawei Zhou, Stanley Bak

来源：arXiv cs.AI（人工智能）

正文

Electrical Engineering and Systems Science > Systems and Control

arXiv:2609.20752v1 (eess)

[Submitted on 17 Sep 2026]

Title:Large Language Models as Falsifiers for Cyber-Physical Systems

Authors:Ali ArjomandBigdeli, Jiawei Zhou, Stanley Bak

View a PDF of the paper titled Large Language Models as Falsifiers for Cyber-Physical Systems, by Ali ArjomandBigdeli and 2 other authors

View PDF

HTML (experimental)

Abstract: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 prompt-based optimization, our key idea is to expose the LLM to semantic information that is natural for language models but absent from standard numerical optimizers, including natural-language input and output names, output trajectories, and critical-time witnesses for the minimum robustness value. These additions enable smarter and more sample-efficient robustness search. On the ARCH-COMP falsification benchmarks, LLM-Falsifier is shown to outperform existing falsification tools based on a range of optimization paradigms, from surrogate-based and Bayesian optimization to search-based testing, on 14 of 21 specifications when measured by the average number of simulations required to find a counterexample.

Comments:

22 pages, 5 figures, 3 tables

Subjects:

Systems and Control (eess.SY); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Software Engineering (cs.SE)

Cite as:

arXiv:2609.20752 [eess.SY]

(or

arXiv:2609.20752v1 [eess.SY] for this version)

https://doi.org/10.48550/arXiv.2609.20752

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

eess.SY · 人工智能 · cs.LO · 软件工程

由「前沿雷达」于 2026-09-20 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。