[2512.18388] Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models

Computer Science > Human-Computer Interaction arXiv:2512.18388 (cs) [Submitted on 20 Dec 2025 (v1), last revised 6 Apr 2026 (this version, v2)] Title:Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models Authors:Chao Wen, Tung Phung, Pronita Mehrotra, Sumit Gulwani, Roger E. Beaty, Tomohiro Nagashima, Adish Singla View a PDF of the paper titled Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models, by Chao Wen and 6 other authors View PDF HTML (experimental) Abstract:Generative AI has democratized content creation, but popular chatbot-based interfaces often prioritize execution, generating fully rendered artifacts right away. This issue can lead to premature convergence and design fixation, where users are being anchored to initial outputs. Recent works have proposed new interfaces to address this issue by supporting exploration, though typically constrained to be semantically close to a user's initial task framing, potentially limiting the creativity of the outcomes. We examine an approach grounded in the Geneplore model of creative cognition and instantiate it in a human-AI co-creation system, HAICo, for creative image generation. HAICo explicitly structures the creative process into two switchable modes: DIVERGENT mode scaffolds the broad exploration of remote conceptual ideas; CONVERGENT mode supports a targeted refinement of selected idea...