Metraipolis › archive › dc_fef0e976d814

What Do CAE Simulation Agents Really Need Beyond a Generic Harness? — arXiv:2609.03718

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03718
License (as archived)
CC0-1.0
Archived
2026-10-17T01:44:49.615Z
SHA-256 of the archived text
39c65bff17e63fc43cf7bbc75e807fc525e42c2b7d18e10a3f7a1786fdb44efc
Stable URL of this page
https://metraipolis.com/documento/dc_fef0e976d814

How to cite

What Do CAE Simulation Agents Really Need Beyond a Generic Harness? — arXiv:2609.03718 — arXiv (en), https://arxiv.org/abs/2609.03718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fef0e976d814 (Metraipolis archive dc_fef0e976d814, sha256 39c65bff17e63fc43cf7bbc75e807fc525e42c2b7d18e10a3f7a1786fdb44efc)
BibTeX
@misc{dcfef0e976d814,
  title = {What Do CAE Simulation Agents Really Need Beyond a Generic Harness? — arXiv:2609.03718},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03718},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fef0e976d814; sha256 39c65bff17e63fc43cf7bbc75e807fc525e42c2b7d18e10a3f7a1786fdb44efc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM, FEniCS, or COMSOL takes real expertise. Large language model (LLM) agents promise to turn a natural-language request into a working simulation, and recent CAE agents add simulation-specific machinery: multi-agent decomposition, domain retrieval, and scripted reflection. That machinery suited weak base models; modern harnesses already supply multi-turn reasoning, tool use, and execution feedback. We ask what a CAE simulation agent still needs beyond a generic harness. With information access and repair budget held fixed, a single-agent harness matches or beats multi-agent specialized systems (FoamBench 96.4\% vs.\ 88.2\%). Ablations trace this to capabilities the harness already provides: execution-feedback repair lifts FoamBench from 71.8\% with no repair round to 96.4\%, while scripted reflection adds nothing. The one input that still helps is domain knowledge supplied as solver tutorials, our largest measured gain (80.9\% to 96.4\%).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computational Engineering, Finance, and Science (cs.CE) ; Computation and Language (cs.CL); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.03718 — 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 2026-10-17T01:11:43.597Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).