Metraipolis › archive › dc_92116d0002b2

Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework — arXiv:2610.11896

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11896
License (as archived)
CC0-1.0
Archived
2026-10-09T06:23:33.881Z
SHA-256 of the archived text
289df60bb378cf8e21e1e7150a5e70ab4f28eefcb8ecc3922fe7dbcb2e40b269
Stable URL of this page
https://metraipolis.com/documento/dc_92116d0002b2

How to cite

Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework — arXiv:2610.11896 — arXiv (en), https://arxiv.org/abs/2610.11896 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_92116d0002b2 (Metraipolis archive dc_92116d0002b2, sha256 289df60bb378cf8e21e1e7150a5e70ab4f28eefcb8ecc3922fe7dbcb2e40b269)
BibTeX
@misc{dc92116d0002b2,
  title = {Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework — arXiv:2610.11896},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11896},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_92116d0002b2; sha256 289df60bb378cf8e21e1e7150a5e70ab4f28eefcb8ecc3922fe7dbcb2e40b269},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11896. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Assembly documentation is a downstream manufacturing artifact that is still usually authored by interpreting CAD models by hand. Structured product data and large language models are both available, yet studies of CAD interpretation, assembly sequence planning, instruction writing, and human oversight have largely proceeded separately. This paper formulates CAD-grounded assembly instruction generation: the production of natural-language assembly procedures constrained by structured engineering information extracted from CAD models. The proposed framework maps a STEP assembly to a typed ProductGraph intermediate representation, derives a precedence order by deterministic topological sorting, realizes each step as language conditioned only on selected graph context, attaches per-step visual documentation, and applies rule-based and model-assisted checks. PDF export remains disabled until a human reviewer resolves every quality flag. The case study establishes endto-end feasibility on a built-in six-part reference assembly: the pipeline preserves a reported assembly order and carries quantity, material, and torque into an exported manual page. Generalization and geometric validation remain open empirical questions. The contribution is an architecture that separates engineering state, deterministic reasoning, grounded language realization, verification, and human release.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.11896 — 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 2026-10-09T05:50:31.689Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).