Metraipolis › archive › dc_839259dc161b

Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models — arXiv:2608.19347

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19347
License (as archived)
CC0-1.0
Archived
2026-10-18T11:49:45.682Z
SHA-256 of the archived text
11058292f2e50f2982b05d6dfebd825b3f6d6f5dc0f4115ee212b4016f0cd9ed
Stable URL of this page
https://metraipolis.com/documento/dc_839259dc161b

How to cite

Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models — arXiv:2608.19347 — arXiv (en), https://arxiv.org/abs/2608.19347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_839259dc161b (Metraipolis archive dc_839259dc161b, sha256 11058292f2e50f2982b05d6dfebd825b3f6d6f5dc0f4115ee212b4016f0cd9ed)
BibTeX
@misc{dc839259dc161b,
  title = {Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models — arXiv:2608.19347},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19347},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_839259dc161b; sha256 11058292f2e50f2982b05d6dfebd825b3f6d6f5dc0f4115ee212b4016f0cd9ed},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Search-based Automated Program Repair (APR) techniques rely on carefully designed mutation operators to explore the space of candidate fixes. Recent advances in Large Language Models (LLMs) suggest that generative models could replace such operators by dynamically proposing repairs. In this paper, we investigate this hypothesis in the context of Cyber-Physical Systems (CPSs) modeled in Simulink/Stateflow. We extend the state-of-the-art FlowRepair approach by replacing a subset of its mutation operators with LLM-generated mutations, enabling more flexible and expressive patch generation. We evaluate the approach on a benchmark of 19 real-world faulty Stateflow models across four CPS domains, using the same experimental setup as FlowRepair for controlled comparison under the same wall-clock budget. Contrary to expectations, in this controlled evaluation, the LLM-based mutation substantially degrades repair performance under the FlowRepair experimental setup. Across the tested LLM variants, the LLM-based repair produced plausible patches for 4-6 models and valid patches for 4 models, compared to 18 and 16, respectively, with the original approach. Our analysis reveals that, in this integration, LLMs struggle with precise symbolic edits, lack behavioral feedback, and generate a noisy search space that hinders effective exploration. Rather than showing a general limitation of LLMs for APR, these findings highlight fundamental limitations of naively integrating LLMs into search-based APR and motivate hybrid approaches that combine structured mutation with generative guidance.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-21 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.19347 — 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 2026-10-18T11:48:10.179Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).