{"slug": "artisancad-an-industrial-level-cad-agent-with-expert-grounded-knowledge", "title": "ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation", "summary": "Researchers introduced ArtisanCAD, an industrial-level CAD agent that uses expert-grounded knowledge distillation to convert ambiguous text prompts into executable CAD programs. The system leverages a CAD intermediate representation (CAD-IR) to encode parameters, operations, and dependencies, enabling it to generate production-ready B-Rep models. On the Text2CAD benchmark, CAD-IR reduced mean Chamfer Distance from 14.83 to 9.88 for intermediate prompts, and on automotive components, it distilled expert CATIA recordings into reusable skills for new variant requests.", "body_md": "arXiv:2607.05750v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/artisancad-an-industrial-level-cad-agent-with-expert-grounded-knowledge", "canonical_source": "https://arxiv.org/abs/2607.05750", "published_at": "2026-07-08 04:00:00+00:00", "updated_at": "2026-07-08 04:04:49.766904+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "generative-ai", "ai-agents", "ai-tools"], "entities": ["ArtisanCAD", "CAD-IR", "CATIA", "Text2CAD", "MCP"], "alternates": {"html": "https://wpnews.pro/news/artisancad-an-industrial-level-cad-agent-with-expert-grounded-knowledge", "markdown": "https://wpnews.pro/news/artisancad-an-industrial-level-cad-agent-with-expert-grounded-knowledge.md", "text": "https://wpnews.pro/news/artisancad-an-industrial-level-cad-agent-with-expert-grounded-knowledge.txt", "jsonld": "https://wpnews.pro/news/artisancad-an-industrial-level-cad-agent-with-expert-grounded-knowledge.jsonld"}}