Metraipolis › archive › dc_88b84129261d
CRAFT: Corrective and Robust Multi-Agent Framework for Text-to-Parametric CAD — arXiv:2611.00076
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00076
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:33:59.780Z
- SHA-256 of the archived text
c6c9f074232d6110a5a645acb4a16e7068acfe0a165462c9c3c967373d057468- Stable URL of this page
https://metraipolis.com/documento/dc_88b84129261d
How to cite
CRAFT: Corrective and Robust Multi-Agent Framework for Text-to-Parametric CAD — arXiv:2611.00076 — arXiv (en), https://arxiv.org/abs/2611.00076 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88b84129261d (Metraipolis archive dc_88b84129261d, sha256 c6c9f074232d6110a5a645acb4a16e7068acfe0a165462c9c3c967373d057468)
BibTeX
@misc{dc88b84129261d,
title = {CRAFT: Corrective and Robust Multi-Agent Framework for Text-to-Parametric CAD — arXiv:2611.00076},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00076},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88b84129261d; sha256 c6c9f074232d6110a5a645acb4a16e7068acfe0a165462c9c3c967373d057468},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00076. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-CAD generation has the potential to make mechanical CAD more accessible, but existing approaches face a trade-off between data dependence and output fidelity. Supervised methods rely on large paired text-model datasets, while zero-shot prompting strategies are often brittle and tend to lose the parametric structure needed for downstream editing and customization. We present CRAFT, a corrective and robust multi-agent framework that produces parametric OpenSCAD programs from natural language without task-specific training. At its core is a JSON intermediate representation that carries symbolic parametric expressions throughout the generation process, so the resulting models remain editable and retain their parametric structure. CRAFT combines semantic understanding, parametric planning, compilation, rendering, self-correction, and component-level verification within a layered recovery process, using multi-view visual feedback to detect and repair geometric errors. Across NopSCADlib, ABC, and Slice-100K, CRAFT is competitive with direct zero-shot baselines in perceptual and geometric quality while exposing substantially more editable parametric structure. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2611.00076 — 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 2026-11-03T10:29:48.665Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).