CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent

TL;DR

CADDesigner is an LLM-powered agent that simplifies conceptual CAD modeling by accepting textual and sketch inputs, engaging interactively with users, and iteratively generating high-quality CAD code.

Contribution

It introduces the Explicit Context Imperative Paradigm (ECIP) and combines iterative visual feedback with structured knowledge storage for improved CAD model generation.

Findings

CADDesigner outperforms baseline methods on conceptual CAD tasks.

The system achieves high-quality CAD code generation with iterative feedback.

Knowledge base storage enables continual improvement of design generation.

Abstract

Computer-Aided Design (CAD) is widely used for conceptual design and parametric 3D modeling, but typically requires a high level of expertise from designers. To lower the entry barrier and facilitate early-stage CAD modeling, we present CADDesigner, an LLM-powered agent for conceptual CAD design. The agent accepts both textual descriptions and sketches as input, engaging in interactive dialogue with users to refine and clarify design requirements through comprehensive requirement analysis. Built upon a novel Explicit Context Imperative Paradigm (ECIP), 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 can be stored in a structured knowledge base, providing a mechanism for continual knowledge accumulation and future improvement of code generation. Experimental results show that CADDesigner achieves competitive performance and outperforms representative baselines on conceptual CAD model generation tasks.