arXiv cs.AI· Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov, Albert Garifullin, Oleg Pavlov, Soslan Kabisov, Vladimir Frolov, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov·· 2 小时前AI 评分42
CADFather:通过协同工具调用实现自主 CAD 重建
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
AI 导读
CADFather 是一个自主智能体系统,通过协调多种工具从 3D 网格中恢复参数化 CAD 程序。视觉语言助手查看目标与中间重建结果的渲染图,决定扩展哪些候选程序、调用哪些工具及何时结束,学习型与算法工具负责提出 CAD 操作,数值优化精调参数,且全程使用预训练模型、无需额外训练。
正文 · 原文
Abstract:Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic system that coordinates complementary tools to recover parametric CAD programs from 3D meshes. A vision-language assistant inspects renders of the target and intermediate reconstructions, then decides which candidate CAD programs to extend, which tools to invoke, how many proposals to generate, and when to finish. Learned and algorithmic tools propose CAD operations, while numerical optimization refines the parameters of existing programs. Proposed or refined programs are executed and evaluated to provide feedback for subsequent decisions. The agent maintains alternative candidate programs for each target part and preserves the best valid result throughout reconstruction. CADFather uses pretrained generation and assistant models without additional training. We evaluate reconstruction quality and execution validity on the full DeepCAD, Fusion360, and MCB test sets, as well as on CADENA-Bench, CADBench, and BenchCAD. We additionally analyze computational cost and the trade-off between cost and reconstruction quality.
| Comments: | 17 pages, 7 figures, 6 tables |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09127 [cs.AI] |
| (or arXiv:2610.09127v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09127 arXiv-issued DOI via DataCite |
Submission history
From: Dmitrii Zhemchuzhnikov [view email]
[v1]
Tue, 6 Oct 2026 21:20:59 UTC (4,125 KB)
[v2]
Wed, 18 Nov 2026 18:43:31 UTC (3,669 KB)
来源:arXiv cs.AI · arxiv.org