ARTISANCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation

Jul 16, 2026

Upload by Levi

Industrial computer-aided design (CAD) for mechanical parts demands long-horizon procedural modeling, robust feature dependencies, editable parametric geometry, and production-grade B-Rep execution. Existing text-to-CAD methods struggle with ambiguous or under-specified prompts and seldom reuse expert procedural knowledge from industrial artifacts. ARTISANCAD introduces CAD intermediate representation (CAD-IR) to distill expert CATIA workflows into reusable parameterized skills and to scaffold intermediate prompts into executable operations. It improves mean Chamfer Distance (14.83 to 9.88) and produces editable CATIA-native B-Rep models for variant requests.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

Abstract

Introduction

Motivation and Gap in Text-to-CAD

Industrial CAD Requirements

arXiv :2607 .05750v2 [ cs .AI] 8 Jul 2026 ARTISANCAD: AN INDUSTRIAL-LEVEL CAD AGENT WITH EXPERT-GROUNDED KNOWLEDGE DISTILLATION Yunhan Xu 1 ,† Qifeng Wu 1 ,† Xunjin Li4 ,† Yuanwei Bin2 ,4 ,∗ Qingsong Yao3 ,∗ Jianghang Gu4 Guan Wang4 Weihao Lv4 Huiyu Yang4 Wenfa Luo5 ,∗ Jiao Xiang5 Yuntian Chen2 Shiyi Chen2 1Peking University, Beijing 100871, China 2Eastern Institute of Technology, Ningbo 315200, Zhejiang, China 3Renmin University of China, Beijing 100872, China 4TenFong Technology Co., Ltd., Shenzhen 518000, Guangdong, China 5IM Motors Technology Co., Ltd., Shanghai 201210, China †Equal contribution. ∗ Corresponding authors: [ybin@eitech.edu.cn](ybin@eitech.edu.cn), [qingsongyao@ruc.edu.cn](qingsongyao@ruc.edu.cn), [luowenfa@immotors.com](luowenfa@immotors.com). ABSTRACT Computer-aided design (CAD) for industrial components requires long-horizon procedural modeling, robust feature dependencies, editable parametric geometry, and production-grade B-Rep execution. Existing text-to-CAD methods have made promising progress in generating CAD programs from natural-language descriptions, but they still struggle when user prompts are ambiguous, underspecified, or only describe high-level design intent. They also rarely exploit expert procedural knowledge naturally available in industrial workflows, such as CATIA operation recordings, macro logs, drawing notes, and engineering descriptions. We present ARTISANCAD , a skill-guided industrial CAD agent with expert-grounded knowledge distillation. The core of ARTISANCAD is CAD intermediate representation (CAD-IR), an executable procedural representation that encodes parameters, ordered operations, MCP tool bindings, dependencies, generated entities, and verification rules. CAD-IR plays two key roles: it first serves as the carrier for distilling expert CAD procedures into reusable parameterized skills; then it provides a procedural scaffold that turns vague or intermediate-level prompts into complete executable CAD operations. ARTISANCAD retrieves expert-derived skills, instantiates and revises CAD-IR, executes the resulting procedure through a dedicated CATIAMCP backend, and uses multi-view visual feedback for iterative refinement, and finally generates production-ready B-Rep models. On the Text2CAD benchmark, CAD-IR improves generation from intermediate prompts by reducing mean Chamfer Distance from 14.83 to 9.88, showing its ability to bridge ambiguous textual intent and executable CAD construction. On four complex automotive components, CAD-IR enables expert CATIA recordings to be distilled into reusable skills, allowing ARTISANCAD to generate editable CATIA-native B-Rep models for new variant requests. Keywords CAD agent · computer-aided design · industrial design · geometric modeling 1 Introduction Computer-aided design (CAD) remains one of the most expertise-intensive workflows in modern engineering and manufacturing. In industrial sectors such as automotive, aerospace, and consumer mechanical product design, engineers use professional CAD systems such as CATIA, Siemens NX, and Creo to construct editable parametric models with sketches, references, constraints, features, and named entities [1, 2] . Unlike casual 3D modeling, industrial CAD authoring is rarely a one-shot shape generation problem. It requires long-horizon procedural modeling, robust feature dependencies, manufacturability-aware construction, and repeated refinement under part-specific requirements such as ArtisanCAD | Expert Experience<br> | | | | --- | --- | --- | | | | | Knowledge Distillation | Part Skill | | --- | | <br> | 0. Knowledge Base Construction Figure 1: Overview of ARTISANCAD . Expert CATIA recordings and drawing notes are distilled into reusable part skills with parameters, checks, template CAD-IR, and ordered operations. Given ambiguous variant requests, ARTISANCAD retrieves the corresponding skill, rewrites CAD-IR through an agent loop, executes it via CA

FAQs

What problem does ARTISANCAD address in industrial CAD generation?

ARTISANCAD targets the mismatch between text-to-CAD systems and real industrial practice, where components require long-horizon procedures, robust dependencies, and production-ready B-Rep models rather than short sketch-and-extrude programs.

What is CAD-IR and what roles does it play in ARTISANCAD?

CAD-IR is an executable intermediate representation that encodes parameters, ordered operations, tool bindings, dependencies, generated entities, and verification rules. It both carries expert procedure distillation into reusable parameterized skills and provides a scaffold to turn intermediate prompts into complete executable CAD operations.

How does ARTISANCAD handle ambiguous or intermediate-level user requests?

ARTISANCAD retrieves relevant expert-derived skills, instantiates and revises CAD-IR through an agent loop, executes the procedure via a dedicated CATIA backend, and uses multi-view visual feedback to iteratively refine the resulting CAD before producing production-ready B-Rep models.

Jul 16, 2026

Upload by Levi