Problem
Research questions and friction points this paper is trying to address.
Synergistic Design
Generative Design Spaces
Ideation Tools
Large Language Models
Scanvas: Discovering and Developing Synergistic Opportunities in Generative Design Spaces
🤖 AI Summary
This study addresses the challenges of identifying synergistic opportunities within generative design spaces and the limitations of existing large language model (LLM) tools constrained to additive paradigms. To overcome these issues, this work proposes a systematic co-creative innovation framework grounded in theoretical strategy operators. The method leverages LLMs to decompose seed idea attributes and operationalizes synergy through three strategy operators: unlocking goals, transforming weaknesses, and sharing components. Furthermore, it establishes a two-stage computational pipeline comprising automated generation followed by interactive search to facilitate comprehensive design space exploration. A user study demonstrates that, compared to baseline methods, the proposed system significantly enhances designers’ capacity to produce high-quality synergistic concepts.
📝 Abstract
Good design is often synergistic, creating super-additive value by linking goals so that existing resources produce greater outcomes. However, finding these synergistic opportunities in sparse design spaces is difficult, and current LLM-supported ideation tools largely default to additive paradigms such as feature blending, variant generation, or local patching. We present Scanvas, an AI-supported system for systematically discovering and developing synergistic design opportunities. Scanvas operationalizes synergy through a two-step computational process: first, it decomposes seed ideas into explicit properties (components, behaviors, surpluses, and issues) to enrich the design space; second, it systematically searches across enriched ideas using three theory-grounded strategy operators: unlocking or strengthening goals, turning weaknesses into resources, and sharing components across functions. We instantiate Scanvas as an auto-generation pipeline and an interactive system. Pipeline ablations and a user study with 12 professional designers demonstrate that Scanvas enables users to surface and develop significantly higher-quality, synergistic concepts compared to LLM ideation baselines.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Synergistic Design
Generative AI
Design Space Exploration
Idea Decomposition
Strategy Operators
🔎 Similar Papers
No similar papers found.
