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

2025-08-01

AI Summary

Non-expert users face significant challenges in efficiently performing CAD conceptual design. Method: This paper proposes a large language model–driven intelligent CAD agent framework featuring: (1) a context-agnostic instruction paradigm (CIP) for robust, cross-scenario CAD code generation; (2) multimodal input fusion—integrating natural language descriptions and hand-drawn sketches—coupled with interactive dialogue to clarify design intent; and (3) an iterative visual feedback mechanism supported by a structured case-based knowledge repository to enable continual agent evolution. Results: Experiments demonstrate state-of-the-art performance on CAD code generation, with substantial improvements in design accuracy, user interaction efficiency, and overall usability over baseline approaches. This work is the first to systematically integrate multimodal understanding, interactive reasoning, and an evolvable knowledge management system into a CAD intelligence agent, empirically validating its feasibility and technical advancement in industrial design applications.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• Reducing expertise barrier in CAD design
• Enhancing design efficiency with LLM-powered agent
• Improving CAD code generation via iterative feedback

Innovation

• Agent uses LLMs for CAD conceptual design
• Accepts text and sketches, refines via dialogue
• Generates CAD code with iterative visual feedback