Abstract
Early-stage cross-disciplinary design often encounters semantic gaps and fragmented problem framings. This study presents IRIS-CEM (Intelligent Reciprocal Interaction System for Co-Evolution Model), a design-driven system that combines AI-generated imagery with a structured semantic card mechanism to support negotiation and collaborative reframing. Deployed through a five-stage workshop process, IRIS-CEM enabled iterative visual–verbal exchanges that surfaced assumptions, bridged disciplinary language, and encouraged perspective shifts. Results show that visual ambiguity prompted abductive reasoning, while the reinterpretation of semantic cards helped teams co-construct shared problem definitions. Moreover, the iterative exchange of AI-generated images and keywords not only reframed the initial problem space but also stimulated the emergence of shared solution directions, demonstrating the toolkit’s dual role in supporting both semantic negotiation and conceptual exploration. Rather than positioning AI as a content generator, IRIS-CEM frames it as a semantic mediator facilitating distributed reasoning and meaning alignment in early-stage collaboration. This study offers a system-level model explaining how ambiguity, reinterpretation, and negotiation interactively shape problem framing across disciplinary boundaries.
Keywords
AI-mediated co-design; Visual consensus; Co-evolution; Cross-disciplinary collaboration
DOI
https://doi.org/10.21606/iasdr.2025.392
Citation
Li, J., Chang, T., Chang, H.,and Lin, C.(2025) IRIS-CEM: An AI-enabled toolkit for visual–verbal collaboration and semantic reframing in design, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.392
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Track 5 - Design Thinking
IRIS-CEM: An AI-enabled toolkit for visual–verbal collaboration and semantic reframing in design
Early-stage cross-disciplinary design often encounters semantic gaps and fragmented problem framings. This study presents IRIS-CEM (Intelligent Reciprocal Interaction System for Co-Evolution Model), a design-driven system that combines AI-generated imagery with a structured semantic card mechanism to support negotiation and collaborative reframing. Deployed through a five-stage workshop process, IRIS-CEM enabled iterative visual–verbal exchanges that surfaced assumptions, bridged disciplinary language, and encouraged perspective shifts. Results show that visual ambiguity prompted abductive reasoning, while the reinterpretation of semantic cards helped teams co-construct shared problem definitions. Moreover, the iterative exchange of AI-generated images and keywords not only reframed the initial problem space but also stimulated the emergence of shared solution directions, demonstrating the toolkit’s dual role in supporting both semantic negotiation and conceptual exploration. Rather than positioning AI as a content generator, IRIS-CEM frames it as a semantic mediator facilitating distributed reasoning and meaning alignment in early-stage collaboration. This study offers a system-level model explaining how ambiguity, reinterpretation, and negotiation interactively shape problem framing across disciplinary boundaries.