Metraipolis › archive › dc_f3212856d91c

RepGen: Reproducing Deep Learning Bugs through Context-Aware Code Generation and Verification — arXiv:2610.41097

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41097
License (as archived)
CC0-1.0
Archived
2026-11-03T05:42:06.999Z
SHA-256 of the archived text
c4ece22df1259107da42068ce3c9cfeafa3cd1b472549d0829c4ef5a5747b965
Stable URL of this page
https://metraipolis.com/documento/dc_f3212856d91c

How to cite

RepGen: Reproducing Deep Learning Bugs through Context-Aware Code Generation and Verification — arXiv:2610.41097 — arXiv (en), https://arxiv.org/abs/2610.41097 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3212856d91c (Metraipolis archive dc_f3212856d91c, sha256 c4ece22df1259107da42068ce3c9cfeafa3cd1b472549d0829c4ef5a5747b965)
BibTeX
@misc{dcf3212856d91c,
  title = {RepGen: Reproducing Deep Learning Bugs through Context-Aware Code Generation and Verification — arXiv:2610.41097},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41097},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3212856d91c; sha256 c4ece22df1259107da42068ce3c9cfeafa3cd1b472549d0829c4ef5a5747b965},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41097. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reproducing deep learning (DL) bugs is challenging because failures can involve source code, models, data, dependencies, and execution environments. Incomplete bug reports further complicate reproduction by omitting essential details. We present RepGen, an open-source tool for reproducing DL bugs through context-aware code generation and iterative verification. Given a bug report and repository, RepGen explores the codebase to build a learning-enhanced context, develop a reproduction plan, and generate candidate scripts. It refines candidates using static checks and LLM feedback to improve their correctness and relevance. When enabled, the tool prepares the execution environment, runs the script, and assesses its output against the reported failure. RepGen provides an interactive command-line interface supporting local and hosted LLMs, configurable execution budgets, and inspectable artifacts, along with a GitHub Action for automated issue processing. The underlying approach reproduced 85 of 106 real-world DL bugs (80.19%). A controlled study with 27 developers showed a 23.35% improvement in reproduction success and a 56.8% reduction in reproduction time.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.41097 — 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 2026-11-03T05:26:27.532Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).