PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 26, 2026Nature Communications4 citationsOpen Access

iDesignGPT enhances conceptual design via large language model agentic workflows

View Full Paper
SLSongkai LiuYSYanqing ShenCZChi Zhang

Key Points

  • The aim is to explore how iDesignGPT can enhance conceptual design using large language models.
  • Integration of large language models with established design methodologies
  • Performance evaluations across six public design challenges
  • Two controlled user studies with different designer profiles
  • iDesignGPT demonstrated competitive novelty, originality, and modularity compared to existing models
  • Novice designers reported lower mental demand and clearer design flow with iDesignGPT
  • Expert assessments confirmed iDesignGPT's effectiveness in conceptual design

Abstract

Conceptual engineering system design faces challenges from traditional methods and emerging AI tools to fully address its inherently complex, dynamic, and creativity-driven demands. iDesignGPT is a framework that integrates large language models with established design methodologies to enable dynamic multi-agent collaboration for problem refinement, information gathering, design space exploration, and evaluation. By incorporating design metrics such as coverage, diversity, and novelty, iDesignGPT provides quantitative insights for early-stage conceptual design. Performance evaluations across six public design challenges show that iDesignGPT achieves competitive novelty and consistently higher originality and modularity than GPT-4o zero-shot, GPT-4o chain-of-thought and Deepseek-r1, based on metrics and expert assessments. Two controlled user studies show positive reception across profiles and, for novice designers, lower mental demand than human-only design and clearer design flow with iDesignGPT. These results establish iDesignGPT as a practical framework for integrating language-model agents with established engineering design methods, enabling metrics-driven support for conceptual design by both expert and novice designers.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69770413722626c4468e9068https://doi.org/10.1038/s41467-026-68672-1
Ask AI
Helpful
Bookmark
Share
View Full Paper