Score: 1

CADDesigner: Conceptual Design of CAD Models Based on General-Purpose Agent

Published: August 1, 2025 | arXiv ID: 2508.01031v2

By: Jingzhe Ni , Xiaolong Yin , Xingyu Lu and more

Potential Business Impact:

Lets anyone design things with words and drawings.

Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing but typically requires a high level of expertise from designers. To lower the entry barrier and improve design efficiency, we present an agent for CAD conceptual design powered by large language models (LLMs). The agent accepts both abstract textual descriptions and freehand sketches as input, engaging in interactive dialogue with users to refine and clarify design requirements through comprehensive requirement analysis. Built upon a novel Context-Independent Imperative Paradigm (CIP), the agent generates high-quality CAD modeling code. During the generation process, the agent incorporates iterative visual feedback to improve model quality. Generated design cases are stored in a structured knowledge base, enabling continuous improvement of the agent's code generation capabilities. Experimental results demonstrate that our method achieves state-of-the-art performance in CAD code generation.

Country of Origin
🇨🇳 China

Page Count
8 pages

Category
Computer Science:
Artificial Intelligence