Metraipolis › archive › dc_e3e37df60da0

An Empirical Evaluation of Using Large Language Models for Automated Model-Based Test Generation — arXiv:2608.27094

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27094
License (as archived)
CC0-1.0
Archived
2026-10-17T16:16:07.229Z
SHA-256 of the archived text
20adedf25a47bb16a79dd9d15c9da97bf91226970f986d944e137d3ff68236ca
Stable URL of this page
https://metraipolis.com/documento/dc_e3e37df60da0

How to cite

An Empirical Evaluation of Using Large Language Models for Automated Model-Based Test Generation — arXiv:2608.27094 — arXiv (en), https://arxiv.org/abs/2608.27094 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3e37df60da0 (Metraipolis archive dc_e3e37df60da0, sha256 20adedf25a47bb16a79dd9d15c9da97bf91226970f986d944e137d3ff68236ca)
BibTeX
@misc{dce3e37df60da0,
  title = {An Empirical Evaluation of Using Large Language Models for Automated Model-Based Test Generation — arXiv:2608.27094},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27094},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3e37df60da0; sha256 20adedf25a47bb16a79dd9d15c9da97bf91226970f986d944e137d3ff68236ca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27094. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models have shown strong potential for software engineering tasks, particularly software testing. Model-based testing (MBT) is a software testing technique. To address the broad scalability challenge for industrial adoption of MBTs, our paper presents an empirical evaluation of Large Language Models (LLMs) for automated model-based test generation, compared with a state-of-the-art model-based testing tool (GraphWalker) and its built-in algorithms (random and quick random for edge and vertex coverage settings). Our evaluation indicates strong potential to optimize and shorten test paths and step sizes using the recent five state-of-the-art LLMs (GPT-5.1, GPT-5.2, Claude Opus 4.5, Claude Sonnet 4.5, and Gemini 2.5 Pro) against four GraphWalker models (two web applications (Parabank and Testinium) and two hardware applications (TLC and RISC-V) ) of escalating complexity.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-28 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.27094 — 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 2026-10-17T15:36:41.157Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).