Metraipolis › archive › dc_7c219707ad63
ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling — arXiv:2609.22325
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22325
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:21:17.537Z
- SHA-256 of the archived text
ed16646291fa449a1d37a716a167c1b19e838e748d85b11a2b9fffe796a84f61- Stable URL of this page
https://metraipolis.com/documento/dc_7c219707ad63
How to cite
ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling — arXiv:2609.22325 — arXiv (en), https://arxiv.org/abs/2609.22325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c219707ad63 (Metraipolis archive dc_7c219707ad63, sha256 ed16646291fa449a1d37a716a167c1b19e838e748d85b11a2b9fffe796a84f61)
BibTeX
@misc{dc7c219707ad63,
title = {ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling — arXiv:2609.22325},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22325},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c219707ad63; sha256 ed16646291fa449a1d37a716a167c1b19e838e748d85b11a2b9fffe796a84f61},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models have shown considerable potential for natural-language-driven parametric CAD modeling. However, a fundamental contradiction exists between their probabilistic generation and the deterministic requirements of CAD modeling, resulting in limitations in reliability, design-intent preservation, and geometric validity. Existing methods typically rely on large-scale annotated datasets, lack explicit modeling of design intent, and underutilize the deterministic capabilities of CAD kernels. To address these limitations, we propose ReliCAD, a unified framework that transforms uncertain LLM generation into reliable parametric CAD modeling. Through explicit design-intent modeling, ReliCAD converts user requirements into structured design specifications and explicitly models geometric relations, topological dependencies, and feature construction order. It then generates constraint-aware parametric instructions and invokes the CAD kernel through an Agent-ready API to perform geometric construction and constraint solving. ReliCAD further records runtime evidence and employs a verification-feedback mechanism to assess consistency between the generated model and the design specifications, enabling error localization and iterative repair. Experiments on the public HistCAD generation dataset and our multi-granularity CAD editing dataset demonstrate that ReliCAD significantly outperforms baseline methods, achieving 99.8\% validity rate and 0.8753 IoU. ReliCAD provides a verifiable, repairable, and generalizable approach to natural-language-interactive CAD modeling. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.22325 — 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 2026-10-09T21:59:59.419Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).