Metraipolis › archive › dc_da38414fc7f7
Large Language Models as Falsifiers for Cyber-Physical Systems — arXiv:2609.20752
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20752
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:24:24.477Z
- SHA-256 of the archived text
7d6cfb4a1831fd9baee7765b7dccf24a5c9ecc3909599a182e4175b825d367f7- Stable URL of this page
https://metraipolis.com/documento/dc_da38414fc7f7
How to cite
Large Language Models as Falsifiers for Cyber-Physical Systems — arXiv:2609.20752 — arXiv (en), https://arxiv.org/abs/2609.20752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da38414fc7f7 (Metraipolis archive dc_da38414fc7f7, sha256 7d6cfb4a1831fd9baee7765b7dccf24a5c9ecc3909599a182e4175b825d367f7)
BibTeX
@misc{dcda38414fc7f7,
title = {Large Language Models as Falsifiers for Cyber-Physical Systems — arXiv:2609.20752},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20752},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da38414fc7f7; sha256 7d6cfb4a1831fd9baee7765b7dccf24a5c9ecc3909599a182e4175b825d367f7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI). Categorie arXiv: Systems and Control (eess.SY) ; Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.20752 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:04:13.985Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).