English

DesignGPT: Multi-Agent Collaboration in Design

Artificial Intelligence 2023-11-21 v1 Human-Computer Interaction

Abstract

Generative AI faces many challenges when entering the product design workflow, such as interface usability and interaction patterns. Therefore, based on design thinking and design process, we developed the DesignGPT multi-agent collaboration framework, which uses artificial intelligence agents to simulate the roles of different positions in the design company and allows human designers to collaborate with them in natural language. Experimental results show that compared with separate AI tools, DesignGPT improves the performance of designers, highlighting the potential of applying multi-agent systems that integrate design domain knowledge to product scheme design.

Keywords

Cite

@article{arxiv.2311.11591,
  title  = {DesignGPT: Multi-Agent Collaboration in Design},
  author = {Shiying Ding and Xinyi Chen and Yan Fang and Wenrui Liu and Yiwu Qiu and Chunlei Chai},
  journal= {arXiv preprint arXiv:2311.11591},
  year   = {2023}
}
R2 v1 2026-06-28T13:25:47.231Z