Saved in:
Bibliographic Details
Main Authors: Shui, Yuan, Guan, Yandong, Zhang, Zhanwei, Hu, Juncheng, Zhang, Jing, Xu, Dong, Yu, Qian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10992
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917406025187328
author Shui, Yuan
Guan, Yandong
Zhang, Zhanwei
Hu, Juncheng
Zhang, Jing
Xu, Dong
Yu, Qian
author_facet Shui, Yuan
Guan, Yandong
Zhang, Zhanwei
Hu, Juncheng
Zhang, Jing
Xu, Dong
Yu, Qian
contents Parametric Computer-Aided Design (CAD) of articulated assemblies is essential for product development, yet generating these multi-part, movable models from high-level descriptions remains unexplored. To address this, we propose ArtiCAD, the first training-free multi-agent system capable of generating editable, articulated CAD assemblies directly from text or images. Our system divides this complex task among four specialized agents: Design, Generation, Assembly, and Review. One of our key insights is to predict assembly relationships during the initial design stage rather than the assembly stage. By utilizing a Connector that explicitly defines attachment points and joint parameters, ArtiCAD determines these relationships before geometry generation, effectively bypassing the limited spatial reasoning capabilities of current LLMs and VLMs. To further ensure high-quality outputs, we introduce validation steps in the generation and assembly stages, accompanied by a cross-stage rollback mechanism that accurately isolates and corrects design- and code-level errors. Additionally, a self-evolving experience store accumulates design knowledge to continuously improve performance on future tasks. Extensive evaluations on three datasets (ArtiCAD-Bench, CADPrompt, and ACD) validate the effectiveness of our approach. We further demonstrate the applicability of ArtiCAD in requirement-driven conceptual design, physical prototyping, and the generation of embodied AI training assets through URDF export.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10992
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation
Shui, Yuan
Guan, Yandong
Zhang, Zhanwei
Hu, Juncheng
Zhang, Jing
Xu, Dong
Yu, Qian
Computer Vision and Pattern Recognition
Parametric Computer-Aided Design (CAD) of articulated assemblies is essential for product development, yet generating these multi-part, movable models from high-level descriptions remains unexplored. To address this, we propose ArtiCAD, the first training-free multi-agent system capable of generating editable, articulated CAD assemblies directly from text or images. Our system divides this complex task among four specialized agents: Design, Generation, Assembly, and Review. One of our key insights is to predict assembly relationships during the initial design stage rather than the assembly stage. By utilizing a Connector that explicitly defines attachment points and joint parameters, ArtiCAD determines these relationships before geometry generation, effectively bypassing the limited spatial reasoning capabilities of current LLMs and VLMs. To further ensure high-quality outputs, we introduce validation steps in the generation and assembly stages, accompanied by a cross-stage rollback mechanism that accurately isolates and corrects design- and code-level errors. Additionally, a self-evolving experience store accumulates design knowledge to continuously improve performance on future tasks. Extensive evaluations on three datasets (ArtiCAD-Bench, CADPrompt, and ACD) validate the effectiveness of our approach. We further demonstrate the applicability of ArtiCAD in requirement-driven conceptual design, physical prototyping, and the generation of embodied AI training assets through URDF export.
title ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10992