CODS : A Theoretical Model for Computational Design Based on Design Space

TL;DR

CODS introduces a generalizable theoretical framework for computational design as a constrained optimization problem over structured design spaces, leveraging large language models for constraint derivation to improve design quality and alignment.

Contribution

It presents a novel, interpretable model that automates constraint derivation in design tasks using LLMs, enabling scalable and controllable AI-powered design automation.

Findings

Superior performance in visualization design and knitwear generation.

Enhanced design quality and user intent alignment.

Effective use of LLMs for constraint derivation in design optimization.

Abstract

We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely on handcrafted heuristics or domain-specific rules, CODS provides a generalizable and interpretable framework that supports diverse design tasks. Given a user requirement and a well-defined design space, CODS automatically derives soft and hard constraints using large language models through a structured prompt engineering pipeline. These constraints guide the optimization process to generate design solutions that are coherent, expressive, and aligned with user intent. We validate our approach across two domains-visualization design and knitwear generation-demonstrating superior performance in design quality, intent alignment, and user preference compared to existing LLM-based methods. CODS offers a unified foundation for scalable, controllable, and AI-powered design automation.