大模型
arxiv.org ·
大型语言模型作为信息物理系统的证伪器
该论文提出 LLM-Falsifier，用 LLM 通过迭代提示最小化 Signal Temporal Logic（STL）鲁棒度，从而为信息物理系统寻找反例。其关键思路是向 LLM 提供数值优化器不具备的语义信息，包括自然语言形式的输入输出名称、输出轨迹以及最小鲁棒度对应的关键时间见证，以提升搜索的样本效率。在 ARCH-COMP 证伪基准上，按找到反例所需的平均仿真次数衡量，该方法在 21 条规约中的 14 条上优于基于代理模型、贝叶斯优化和搜索式测试的现有工具。
AI推荐理由 arXiv 预印本，作者与摘要明确，方法描述具体（将 STL 鲁棒度最小化与 LLM 迭代提示结合，并引入自然语言输入输出名、输出轨迹和关键时间见证等语义信息），在 ARCH-COMP 基准的 21 条规约中有 14 条以平均仿真次数衡量优于代理模型、贝叶斯优化和搜索式测试等现有工具。属于 LLM 用于形式化验证/信息物理系统证伪的新方向，对 AI 与系统安全交叉领域有参考价值；但结果仅来自论文自述的基准对比，尚无独立复现或代码发布证据，且为预印本未经同行评审，故兴趣分未给更高。
72
正文
Electrical Engineering and Systems Science > Systems and Control
arXiv:2609.20752 (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:
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)
Submission history
From: Ali Arjomandbigdeli [view email]
[v1]
Thu, 17 Sep 2026 17:40:04 UTC (244 KB)
Full-text links:
Access Paper:
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)
TeX Source
view license
Current browse context:
eess.SY
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
cs.LO
cs.SE
cs.SY
eess
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)