Metraipolis › archive › dc_d22bbdaddfdd

Designing Collaborative AI-Driven Workflows for Scientific Software Engineering — arXiv:2610.09995

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09995
License (as archived): CC0-1.0
Archived: 2026-10-08T12:37:55.396Z
SHA-256 of the archived text: c0fd2fd9f5de71f42205c1dfa22cbac88eda4bfd8f65e7467370304ccfdd0f76
Stable URL of this page: https://metraipolis.com/documento/dc_d22bbdaddfdd

How to cite

Designing Collaborative AI-Driven Workflows for Scientific Software Engineering — arXiv:2610.09995 — arXiv (en), https://arxiv.org/abs/2610.09995 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d22bbdaddfdd (Metraipolis archive dc_d22bbdaddfdd, sha256 c0fd2fd9f5de71f42205c1dfa22cbac88eda4bfd8f65e7467370304ccfdd0f76)

BibTeX

@misc{dcd22bbdaddfdd,
  title = {Designing Collaborative AI-Driven Workflows for Scientific Software Engineering — arXiv:2610.09995},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09995},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d22bbdaddfdd; sha256 c0fd2fd9f5de71f42205c1dfa22cbac88eda4bfd8f65e7467370304ccfdd0f76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09995. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic artificial intelligence systems can carry out a broad range of tasks in software engineering and scientific research, from writing and translating code to running workflows for data analysis and visualization. In scientific computing, the difficulty is verifying that agent-generated code is both correct and understandable to teams whose members bring different areas of expertise. We therefore argue that these systems are best used within collaborative team structures rather than as full automation. In the workflows we propose, domain experts write the specification and plan, and agents operate under a deterministic orchestration pattern to write the target code. Each stage ends with a numerical comparison against the reference code and requires human review and approval before the next begins. We evaluate these workflows on the translation of a large high-energy physics application from Fortran to C++, running the same task under different orchestrators, design patterns, and models. Across fourteen experiments, a simple author--reviewer loop with enforced limits completed a comparable number of files to a multi-agent workflow at about one-third of the cost per file.

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/2610.09995 — 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 2026-10-08T12:14:30.251Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).