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

2026-07-06

AI Summary

This work addresses the limitations of existing text-to-CAD generation methods, which struggle with ambiguous or high-level design intents and fail to effectively incorporate industrial expert knowledge. To bridge this gap, the authors propose an industrial-grade CAD agent based on expert knowledge distillation, introducing for the first time an executable CAD Intermediate Representation (CAD-IR) as a unified carrier. This framework translates expert operation logs into parameterized skills and integrates multi-view visual feedback with a CATIA-MCP execution engine to automatically translate semantic prompts into editable, production-ready B-Rep models. Evaluated on the Text2CAD benchmark, the method reduces the average Chamfer Distance for intermediate prompts from 14.83 to 9.88 and successfully generates native CATIA models of four complex automotive components.

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 \algname, a skill-guided industrial CAD agent with expert-grounded knowledge distillation. The core of \algname 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. \algname retrieves expert-derived skills, instantiates and revises CAD-IR, executes the resulting procedure through a dedicated CATIA-MCP 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 \algname to generate editable CATIA-native B-Rep models for new variant requests.

Problem

• text-to-CAD
• expert knowledge
• procedural modeling
• industrial CAD
• ambiguous prompts

Innovation

• CAD-IR
• knowledge distillation
• procedural modeling
• expert-guided agent
• B-Rep generation