From Idea to CAD: A Language Model-Driven Multi-Agent System for Collaborative Design
This approach could improve design efficiency for both industry experts and hobbyists, though it appears incremental as it adapts existing multi-agent and VLM methods to CAD.
The paper tackles the challenge of automating digital model creation in CAD by introducing a Vision Language Model-based multi-agent system that generates models from sketches or text, enabling iterative refinement with users.
Creating digital models using Computer Aided Design (CAD) is a process that requires in-depth expertise. In industrial product development, this process typically involves entire teams of engineers, spanning requirements engineering, CAD itself, and quality assurance. We present an approach that mirrors this team structure with a Vision Language Model (VLM)-based Multi Agent System, with access to parametric CAD tooling and tool documentation. Combining agents for requirements engineering, CAD engineering, and vision-based quality assurance, a model is generated automatically from sketches and/ or textual descriptions. The resulting model can be refined collaboratively in an iterative validation loop with the user. Our approach has the potential to increase the effectiveness of design processes, both for industry experts and for hobbyists who create models for 3D printing. We demonstrate the potential of the architecture at the example of various design tasks and provide several ablations that show the benefits of the architecture's individual components.