iDesignGPT: large language model agentic workflows boost engineering design

Engineering design, a cornerstone of technological innovation, faces persistent challenges from the rigidity of traditional methods and the insufficient responsiveness of emerging AI tools to fully address its inherently complex, dynamic, and creativity-driven demands. Here we introduce iDesignGPT, a novel framework that integrates large language model with established design methodologies to enable dynamic multi-agent collaboration for problem refinement, information gathering, design space exploration, and iterative optimization. By incorporating design metrics such as coverage, diversity, and novelty, iDesignGPT provides decision-enabling, data-driven insights for conceptual engineering design evaluation. Our results reveal that iDesignGPT surpasses benchmark models in generating innovative, modular, and rational solutions, particularly in exploratory, open-ended scenarios prioritizing creativity and adaptability. User studies, involving both students and experienced engineers, validate its ability to uncover hidden requirements, foster creativity, and enhance workflow transparency. Collectively, these findings position iDesignGPT as a scalable platform that lowers the expertise barrier, fosters interdisciplinary collaboration, and expands the transformative potential of AI-assisted engineering design.