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

2025-12-20

AI Summary

Current generative AI interfaces predominantly employ linear interaction patterns, leading users to prematurely converge on suboptimal “good-enough” solutions and suffer from design fixation—thereby inhibiting creative exploration. To address this, we propose a staged human-AI co-creation paradigm grounded in Wallas’s creative process model, explicitly decoupling divergent exploration from convergent optimization. Our approach introduces two novel scaffolding mechanisms: (1) concept-level brainstorming to foster open-ended ideation, and (2) parametric intent externalization to make user intentions explicit and editable. Technically, the system integrates diffusion models, an interpretable parameter interface, structured prompt guidance, and temporal task orchestration. A controlled user study demonstrates that, compared to ChatGPT-style linear interaction, our system significantly reduces design fixation (p < 0.01), improves intent alignment (+38%), enhances perceived controllability (+42%), and effectively supports nonlinear creative workflows.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Generative AI has begun to democratize creative work, enabling novices to produce complex artifacts such as code, images, and videos. However, in practice, existing interaction paradigms often fail to support divergent exploration: users tend to converge too quickly on early ``good enough'' results and struggle to move beyond them, leading to premature convergence and design fixation that constrains their creative potential. To address this, we propose a structured, process-oriented human-AI co-creation paradigm including divergent and convergent thinking stages, grounded in Wallas's model of creativity. To avoid design fixation, our paradigm scaffolds both high-level exploration of conceptual ideas in the early divergent thinking phase and low-level exploration of variations in the later convergent thinking phrase. We instantiate this paradigm in HAIExplore, an image co-creation system that (i) scaffolds divergent thinking through a dedicated brainstorming stage for exploring high-level ideas in a conceptual space, and (ii) scaffolds convergent refinement through an interface that externalizes users' refinement intentions as interpretable parameters and options, making the refinement process more controllable and easier to explore. We report on a within-subjects study comparing HAIExplore with a widely used linear chat interface (ChatGPT) for creative image generation. Our findings show that explicitly scaffolding the creative process into brainstorming and refinement stages can mitigate design fixation, improve perceived controllability and alignment with users' intentions, and better support the non-linear nature of creative work. We conclude with design implications for future creativity support tools and human-AI co-creation workflows.

Problem

• Mitigate design fixation in human-AI co-creation
• Scaffold divergent and convergent thinking stages
• Improve controllability and alignment with user intentions

Innovation

• Structured co-creation paradigm with divergent and convergent thinking stages
• Scaffolding high-level idea exploration and low-level variation refinement
• Externalizing refinement intentions as interpretable parameters for controllability