NexusAI: Enabling Design Space Exploration of Ideas through Cognitive Abstraction and Functional Decomposition

TL;DR

NexusAI leverages cognitive abstraction to transform LLM-generated ideas into a structured, decomposable design space, enhancing exploration and reducing fixation in human-AI co-creation.

Contribution

The paper introduces the CA pipeline and NexusAI system, enabling decomposition, abstraction, and recombination of ideas to improve creative design exploration.

Findings

NexusAI significantly improves design space exploration.

It reduces cognitive overhead during ideation.

It facilitates perspective reframing in creative tasks.

Abstract

Large Language Models (LLMs) offer vast potential for creative ideation; however, their standard interaction paradigm often produces unstructured textual outputs that lead users to prematurely converge on sub-optimal ideas-a phenomenon known as fixation. While recent creativity tools have begun to structure these outputs, they remain compositionally opaque: ideas are organized as monolithic units that cannot be decomposed, abstracted, or recombinable at a sub-idea level. To address this, we propose Cognitive Abstraction (CA), a computational pipeline that transforms raw LLM-generated inspiration into a navigable and transformable design space. We implement this pipeline in NexusAI, a prototype diagramming system that supports (I) decomposition of inspiration into typed functional fragments, (II) multi-level abstraction to externalize mental scaling, and (III) cross-dimensional recombination to spark novel design directions. A within-subject user study (N=14) demonstrates that NexusAI significantly improves design space exploration, reduces cognitive overhead, and facilitates perspective reframing compared to a baseline. Our work contributes: (1) a characterization of "compositional opacity" as a barrier in human-AI co-creation; (2) the CA pipeline for operationalizing creative cognitive primitives at scale; and (3) empirical evidence that structured, multi-level representations can effectively mitigate fixation and support divergent exploration.