Metraipolis › archive › dc_286bd6b4e9a3

EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? — arXiv:2609.37686

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37686
License (as archived)
CC0-1.0
Archived
2026-10-07T16:24:03.981Z
SHA-256 of the archived text
25676aa51bfcb5ddd95179e95f36168b45a950255034aeca15ad94ce5ea8d7c0
Stable URL of this page
https://metraipolis.com/documento/dc_286bd6b4e9a3

How to cite

EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? — arXiv:2609.37686 — arXiv (en), https://arxiv.org/abs/2609.37686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_286bd6b4e9a3 (Metraipolis archive dc_286bd6b4e9a3, sha256 25676aa51bfcb5ddd95179e95f36168b45a950255034aeca15ad94ce5ea8d7c0)
BibTeX
@misc{dc286bd6b4e9a3,
  title = {EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? — arXiv:2609.37686},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_286bd6b4e9a3; sha256 25676aa51bfcb5ddd95179e95f36168b45a950255034aeca15ad94ce5ea8d7c0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous agents have made rapid progress in general-purpose computer use, but reliable automation of professional industrial engineering remains out of reach, as engineering workflows demand reasoning over geometric and physical constraints and dependencies preserved across software and design stages. We present EngiWorld, the first benchmark structured around the complete design loop: 1,301 expert-curated tasks spanning 6 engineering domains (CAD, CAE, CAM, BIM, EDA, and 3D visualization) and 26 professional software platforms, with both GUI and CLI interfaces and 6 task types ranging from software-selection to open-ended tasks. We further introduce an artifact-centric evaluation methodology built on a unified domain-verifier suite, which programmatically checks the geometric validity, physical feasibility, and rule compliance of final and intermediate artifacts, and scores quantitative design tasks continuously by specification attainment rather than binary success. Evaluation of seven frontier models reveals a substantial capability gap: the strongest model achieves an EngiScore of only 44.3, and just 3.6% of multi-software attempts succeed. EngiWorld provides the first rigorous foundation for measuring progress toward agents that operate professional engineering software end to end.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.37686 — 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 2026-10-07T15:54:53.647Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).