Large Language Models for Computer-Aided Design: A Survey

2025-05-13

AI Summary

Despite the growing integration of large language models (LLMs) into computer-aided design (CAD), there exists no systematic survey or unified framework addressing their synergistic application in this domain. Method: This work conducts the first comprehensive, systematic study of LLM–CAD co-evolution, synthesizing literature and technical analysis to propose a novel six-category application taxonomy grounded in industrial requirements. It examines both closed-source (e.g., ChatGPT) and open-source (e.g., DeepSeek) LLMs, integrating CAD modeling workflows, instruction engineering, multimodal interfaces, and domain-specific knowledge alignment techniques. Contribution/Results: We release an open-source LLM-CAD classification knowledge base on GitHub, identify critical bottlenecks—including semantic gap, 3D representation fidelity, and workflow integration—and outline five key research directions: scalable prompt engineering, CAD-specialized fine-tuning, 3D semantic understanding, bidirectional LLM–CAD interfaces, and evaluation benchmarks for design intelligence.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large Language Models (LLMs) have seen rapid advancements in recent years, with models like ChatGPT and DeepSeek, showcasing their remarkable capabilities across diverse domains. While substantial research has been conducted on LLMs in various fields, a comprehensive review focusing on their integration with Computer-Aided Design (CAD) remains notably absent. CAD is the industry standard for 3D modeling and plays a vital role in the design and development of products across different industries. As the complexity of modern designs increases, the potential for LLMs to enhance and streamline CAD workflows presents an exciting frontier. This article presents the first systematic survey exploring the intersection of LLMs and CAD. We begin by outlining the industrial significance of CAD, highlighting the need for AI-driven innovation. Next, we provide a detailed overview of the foundation of LLMs. We also examine both closed-source LLMs as well as publicly available models. The core of this review focuses on the various applications of LLMs in CAD, providing a taxonomy of six key areas where these models are making considerable impact. Finally, we propose several promising future directions for further advancements, which offer vast opportunities for innovation and are poised to shape the future of CAD technology. Github: https://github.com/lichengzhanguom/LLMs-CAD-Survey-Taxonomy

Problem

• Exploring LLMs' integration with CAD for workflow enhancement
• Surveying applications of LLMs in 3D modeling and design
• Identifying future AI-driven innovations in CAD technology

Innovation

• Integration of LLMs with CAD workflows
• Taxonomy of six key LLM applications in CAD
• Survey of closed-source and public LLMs for CAD