IDEA: Augmenting Design Intelligence through Design Space Exploration

TL;DR

This paper introduces IDEA, a framework that enhances design decision-making by formalizing design spaces and using AI-driven exploration to generate effective, domain-specific design solutions.

Contribution

The paper presents a novel structured representation of design spaces and integrates large language models with Monte Carlo Tree Search for automated design exploration.

Findings

Effective in data-driven article composition

Generates high-quality pictorial visualizations

Validated through expert interviews and user studies

Abstract

Design spaces serve as a conceptual framework that enables designers to explore feasible solutions through the selection and combination of design elements. However, effective decision-making remains heavily dependent on the designer's experience, and the absence of mathematical formalization prevents computational support for automated design processes. To bridge this gap, we introduce a structured representation that models design spaces with orthogonal dimensions and discrete selectable elements. Building on this model, we present IDEA, a decision-making framework for augmenting design intelligence through design space exploration to generate effective outcomes. Specifically, IDEA leverages large language models (LLMs) for constraint generation, incorporates a Monte Carlo Tree Search (MCTS) algorithm guided by these constraints to explore the design space efficiently, and instantiates abstract decisions into domain-specific implementations. We validate IDEA in two design scenarios: data-driven article composition and pictorial visualization generation, supported by example results, expert interviews, and a user study. The evaluation demonstrates the IDEA's adaptability across domains and its capability to produce superior design outcomes.