Beyond Input-Output: Rethinking Creativity through Design-by-Analogy in Human-AI Collaboration

2026-02-10

AI Summary

This study addresses the growing homogenization of creative content driven by the widespread adoption of foundation models and the limitations of current AI-assisted design approaches, which are largely confined to input–output paradigms and early ideation stages, thereby reinforcing design fixation. To overcome these constraints, the work reimagines Design by Analogy (DbA) not merely as a tool for initial inspiration but as a mediating mechanism for human–AI collaboration throughout the entire creative process. Drawing on a systematic literature review of 85 studies and grounded in cognitive science theories, the research proposes a seven-stage creative process model, identifies six representational forms, and extends DbA’s applicability across creative industries, intelligent manufacturing, and educational services. In doing so, it reconceptualizes the theoretical framework for AI-supported creativity, offering a novel pathway for human–AI co-creation while highlighting key opportunities and potential risks.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Web Mining and Content Analysis: Models for Web evolution

Abstract

While the proliferation of foundation models has significantly boosted individual productivity, it also introduces a potential challenge: the homogenization of creative content. In response, we revisit Design-by-Analogy (DbA), a cognitively grounded approach that fosters novel solutions by mapping inspiration across domains. However, prevailing perspectives often restrict DbA to early ideation or specific data modalities, while reducing AI-driven design to simplified input-output pipelines. Such conceptual limitations inadvertently foster widespread design fixation. To address this, we expand the understanding of DbA by embedding it into the entire creative process, thereby demonstrating its capacity to mitigate such fixation. Through a systematic review of 85 studies, we identify six forms of representation and classify techniques across seven stages of the creative process. We further discuss three major application domains: creative industries, intelligent manufacturing, and education and services, demonstrating DbA's practical relevance. Building on this synthesis, we frame DbA as a mediating technology for human-AI collaboration and outline the potential opportunities and inherent risks for advancing creativity support in HCI and design research.

Problem

• creativity homogenization
• design fixation
• Design-by-Analogy
• human-AI collaboration
• foundation models

Innovation

• Design-by-Analogy
• human-AI collaboration
• creative process
• design fixation
• foundation models