Metraipolis › archive › dc_7adca5d32e58

Code Health in LLM-Based Test Generation: Effectiveness and Token Efficiency — arXiv:2608.18645

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18645
License (as archived)
CC0-1.0
Archived
2026-10-18T13:54:46.084Z
SHA-256 of the archived text
b536123414ee51c32a029ca5d7e640dc1379808cb6fb5022ec7316d58984d854
Stable URL of this page
https://metraipolis.com/documento/dc_7adca5d32e58

How to cite

Code Health in LLM-Based Test Generation: Effectiveness and Token Efficiency — arXiv:2608.18645 — arXiv (en), https://arxiv.org/abs/2608.18645 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7adca5d32e58 (Metraipolis archive dc_7adca5d32e58, sha256 b536123414ee51c32a029ca5d7e640dc1379808cb6fb5022ec7316d58984d854)
BibTeX
@misc{dc7adca5d32e58,
  title = {Code Health in LLM-Based Test Generation: Effectiveness and Token Efficiency — arXiv:2608.18645},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18645},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7adca5d32e58; sha256 b536123414ee51c32a029ca5d7e640dc1379808cb6fb5022ec7316d58984d854},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18645. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents powered by Large Language Models (LLMs) are now prominent in software engineering. Previous work has shown that AI tools perform better on high-quality source code that is easy to maintain. In this study, we investigate how the effectiveness of LLM-generated unit tests varies across maintainability levels measured by CodeScene's CodeHealth (CH). We assess test effectiveness using traditional coverage metrics and mutation score across Python, Java, and C++. Moreover, we study how code with different levels of CH translates into input tokens using common industrial tokenizers. Our results suggest that CH provides a weak but consistent signal of LLM-generated test effectiveness and is negatively correlated with input-token count. These findings provide further evidence for a relationship between maintainability and LLM-based software development.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-20 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.18645 — 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 2026-10-18T13:51:24.529Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).