[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81935-en":3,"doc-seo-81935-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},81935,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Foundation Models for Automatic CAD Generation","Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable automatic creation of parametric 3D CAD designs from natural-language specifications. This chapter reports an empirical study using a unified evaluation pipeline and a curated benchmark of 97 engineering design problems. It presents LLMForge, a multi-model text-to-CAD framework combining JSON-schema validation, analytic feature scoring, mesh synthesis, and multi-round iterative refinement under two critique regimes. IterTracer uses geometry-aware visual metrics, while IterVision uses a VLM semantic critic for richer spatial assessment.","arXiv :2607 .05573v 1 [ cs .AI] 6 Jul 2026  \nFoundation Models for Automatic CAD Generation  \nJ. de Curt`o1,2 , Victoria Guill´en2,3 and [I. de](I. de) Zarz`a4  \n1 Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center,  \n08034 Barcelona, Spain  \n2 Escuela T´ecnica Superior de Ingenier´ıa (ICAI), Universidad Pontificia Comillas, 28015 Madrid, Spain  \n3 Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea  \n4 Human Centered AI, Data & Software, LUXEMBOURG Institute of Science and Technology, L-4362  \nEsch-sur-Alzette, Luxembourg  \nAbstract. Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have opened new pathways for the automatic generation of parametric three-dimensional designs from natural-language specifications. This chapter presents a comprehensive empirical study on the use of modern foundation models for automatic Computer-Aided Design (CAD) generation of mechanical parts, structured around a unified evaluation pipeline and a curated benchmark suite of 97 engineering design problems. We introduce LLMForge, a multi-model text-to-CAD framework that integrates JSON-schema validation, analytic feature scoring, mesh synthesis, and a multi-round iterative refinement loop, studied under two distinct critique regimes. The first regime, IterTracer, employs a Phongshaded ray-trace renderer coupled with a suite of analytic visual metrics, silhouette IoU, hole visibility, edge clearance, and aspect-ratio conformance, to provide lightweight, geometry-aware feedback across successive generation rounds. The second regime, IterVision, replaces the analytic scorer with a VLMbased semantic critic (Qwen2.5-VL-72B) that evaluates rendered views of each candidate geometry through chain-of-thought visual reasoning, enabling richer assessment of spatial coherence and design intent. Using a benchmark spanning four canonical geometry families, rectangular plates with holes and bolt circles, multi-feature boxes, flanged cylinders, and L-brackets, we evaluate seven state-of-theart foundation models: DeepSeek-V3.2, Qwen3-235B-A22B, Llama-3.3-70B, Gemma-3-27B, GLM-4.5, MiniMax-M2.1, and INTELLECT. Under IterTracer, the four highest-ranked models form a tight performance cluster (µoverall ∈ [0 .885 , 0.890]) with mesh success rates of 98.97%, demonstrating that compact instruction-tuned models can attain reliability competitive with substantially larger systems.  \nThe addition of VLM-based critique in IterVision yields 100% watertight mesh generation on the leading model while surfacing systematic difficulty on rotationally symmetric geometries such as cylinders, where visual and semantic scoring diverge most markedly. The chapter discusses benchmark design principles, model failure modes, CAD-oriented prompting strategies, and implications for industrial engineering workflows. We conclude by identifying future research directions for scalable, automated mechanical design within Global Applied AI pipelines.  \nKeywords: Large Language Models, Vision-Language Models, Text-to-CAD, Parametric Design, Foundation Models, Engineering Automation  \n1 Introduction  \nThe automation of mechanical design has long been a central aspiration of engineering informatics. Traditional Computer-Aided Design (CAD) workflows demand expert knowledge of constraint-based parametric modelling, scripting languages, and domain conventions that are largely inaccessible to non-specialists and difficult to integrate into automated processing chains. The emergence of large language models capable of generating structured code from natural-language instructions represents a qualitative shift in this landscape: a practitioner can now describe a mechanical part in plain English, “a 150mm × 100mm × 4mm plate with a centred bolt circle of six equally-spaced M5 holes, diameter 60mm”, and expect a computational agent to translate that intent directly into a valid, manufacturable three","cbCainhIWkmDYZuq","https://ap.wps.com/l/cbCainhIWkmDYZuq","pdf",1650081,1,11,"English","en",105,"# Introduction\n# Contributions\n## IterTracer\n## IterVision","[{\"question\":\"What is the main goal of the chapter?\",\"answer\":\"To evaluate foundation models for automatic CAD generation from natural-language specifications, focusing on reliable parametric mechanical design creation and iterative refinement.\"},{\"question\":\"How does LLMForge improve the quality of generated CAD geometries?\",\"answer\":\"It validates outputs with JSON-schema, scores candidates across multiple axes (schema, mesh soundness, feature adherence, visual fidelity), synthesizes meshes, and performs up to four rounds of iterative refinement using structured critique.\"},{\"question\":\"What is the difference between IterTracer and IterVision?\",\"answer\":\"IterTracer provides lightweight, geometry-aware feedback using analytic visual metrics from rendered views, while IterVision replaces the analytic scorer with a VLM semantic critic (Qwen2.5-VL-72B) that evaluates rendered views via visual reasoning.\"}]",1784177141,28,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"foundation-models-for-automatic-cad-generation","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/foundation-models-for-automatic-cad-generation/81935/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of the chapter?","Question",{"text":74,"@type":75},"To evaluate foundation models for automatic CAD generation from natural-language specifications, focusing on reliable parametric mechanical design creation and iterative refinement.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does LLMForge improve the quality of generated CAD geometries?",{"text":79,"@type":75},"It validates outputs with JSON-schema, scores candidates across multiple axes (schema, mesh soundness, feature adherence, visual fidelity), synthesizes meshes, and performs up to four rounds of iterative refinement using structured critique.",{"name":81,"@type":72,"acceptedAnswer":82},"What is the difference between IterTracer and IterVision?",{"text":83,"@type":75},"IterTracer provides lightweight, geometry-aware feedback using analytic visual metrics from rendered views, while IterVision replaces the analytic scorer with a VLM semantic critic (Qwen2.5-VL-72B) that evaluates rendered views via visual reasoning.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]