Metraipolis › archive › dc_664d39dbf452

Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency — arXiv:2608.14065

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14065
License (as archived)
CC0-1.0
Archived
2026-10-19T02:21:18.129Z
SHA-256 of the archived text
33ea8f6f5c064a39fb0c963638a1e56f34b2d6f0d385c1e221ef78aa35385737
Stable URL of this page
https://metraipolis.com/documento/dc_664d39dbf452

How to cite

Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency — arXiv:2608.14065 — arXiv (en), https://arxiv.org/abs/2608.14065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_664d39dbf452 (Metraipolis archive dc_664d39dbf452, sha256 33ea8f6f5c064a39fb0c963638a1e56f34b2d6f0d385c1e221ef78aa35385737)
BibTeX
@misc{dc664d39dbf452,
  title = {Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency — arXiv:2608.14065},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14065},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_664d39dbf452; sha256 33ea8f6f5c064a39fb0c963638a1e56f34b2d6f0d385c1e221ef78aa35385737},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Background: Software bugs remain a critical challenge in development, necessitating effective Automated Program Repair (APR) techniques. While Large Language Model (LLM)-based APR systems have shown promise, prior studies primarily focus on overall repair effectiveness. The effects of bug complexity, fault localization, reasoning settings, and repair cost-effectiveness remain insufficiently explored. Aims: This study presents a comprehensive empirical analysis of LLM-based APR, focusing on how repair performance is shaped by bug complexity, fault localization, reasoning settings, and costs. Method: We evaluate two APR techniques (ChatRepair and CodeCorrector) using three LLMs (DeepSeek, GPT, and Llama), and examine their performance across diverse levels of bug complexity and localization strategies through a multi-dimensional empirical framework and statistical analysis. Results: Although structurally complex bugs and imprecise fault localization make repair more challenging, LLM-based APR techniques still achieve competitive repair effectiveness. Imprecise fault localization can substantially enlarge the performance gap between APR techniques. Furthermore, higher-cost LLMs and stronger reasoning settings do not consistently yield better cost-efficiency, revealing a nontrivial trade-off between repair effectiveness and computational cost. Conclusions: Over 50% of moderately complex bugs can be repaired by low-cost LLM-based APR techniques. The repair effectiveness gap between APR techniques becomes larger as fault localization becomes less precise. GPT-5 repairs 7 and 39 more complex bugs than DeepSeek-V4-pro and DeepSeek-V3.2, respectively; whereas the total repair cost of DeepSeek-V3.2 shows the best cost-efficiency performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14065 — 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 2026-10-19T02:02:02.900Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).