Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
Researchers have developed ProCAD, a novel framework for text-to-CAD generation that addresses inconsistencies and ambiguities in user prompts. ProCAD employs a proactive clarifying agent to ask targeted questions before code synthesis, ensuring a self-consistent specification. This approach significantly enhances robustness to ambiguous inputs and outperforms existing models, including Claude Sonnet 4.5, by reducing geometric errors and invalidity ratios. The framework's code and datasets are publicly available. AI
IMPACT Enhances robustness in text-to-CAD systems by proactively resolving prompt ambiguities, setting a new benchmark for accuracy.