Metraipolis › archive › dc_f686262ec151

From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation? — arXiv:2610.41267

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41267
License (as archived): CC0-1.0
Archived: 2026-11-03T07:21:44.202Z
SHA-256 of the archived text: b1c569a74eb6a7f36633d96c85d964dbf68c9f1261de5b069755396b52a5fd32
Stable URL of this page: https://metraipolis.com/documento/dc_f686262ec151

How to cite

From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation? — arXiv:2610.41267 — arXiv (en), https://arxiv.org/abs/2610.41267 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f686262ec151 (Metraipolis archive dc_f686262ec151, sha256 b1c569a74eb6a7f36633d96c85d964dbf68c9f1261de5b069755396b52a5fd32)

BibTeX

@misc{dcf686262ec151,
  title = {From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation? — arXiv:2610.41267},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41267},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f686262ec151; sha256 b1c569a74eb6a7f36633d96c85d964dbf68c9f1261de5b069755396b52a5fd32},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41267. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Turning an engineering request into a simulation requires consistent geometry, physics, boundary conditions, and numerical settings. Recent agent-assisted systems automate simulation setup, but successful execution alone does not establish whether the specification preserves the intended problem or correctly handles missing information. We study whether agents can reliably construct complete executable JSON specifications for automated geometry creation, meshing, PDE solving, and result export. Our workflow combines model extraction with deterministic scientific and capability checks, explicit clarification, and validated local patches that preserve unrelated accepted fields. We evaluate specification correctness, execution completion, and numerical verification separately. On 120 template-related requests, the full workflow achieves 98.3% correct first-turn specification and decision outcomes, compared with 92.5% for schema-assisted single shot and 82.5% for model-only: gains of 5.8 and 15.8 percentage points, respectively. It makes no false-ready decisions among the 42 requests requiring clarification or rejection. Component ablations identify contributions from scientific checks and conditional repair. Separate downstream studies cover 1D, 2D, and 3D steady and unsteady, linear and nonlinear problems, including flow and elasticity with complex three-dimensional wing geometries. A 30-case gallery demonstrates automated execution from retained JSON specifications, while 9 of 12 selected live user-to-results tests achieve joint specification, execution, export, and numerical-reference success (75.0%). These results support traceable, engineer-reviewed simulation assistance within the tested scope, while fresh-response regressions identify consistency as a priority for further improvement.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE).
Pagina del lavoro: https://arxiv.org/abs/2610.41267 — 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 2026-11-03T07:19:48.809Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).