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

2025-06-23

AI Summary

The absence of a general, interpretable computational design framework hinders intent-driven, domain-agnostic design automation. Method: We propose a constraint-optimization approach grounded in design space modeling: design tasks are formalized as optimization problems with soft and hard constraints; large language models (LLMs) automatically parse user intent and generate structured constraints; structured prompt engineering and efficient optimization algorithms jointly enable intent-guided design synthesis. Contribution/Results: We introduce the first general, interpretable computational design theory model applicable across domains. Evaluated on visual design and knit pattern generation, our framework significantly outperforms existing LLM-based methods in design quality, intent alignment, and user preference fidelity—demonstrating its effectiveness, interpretability, and cross-domain scalability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Framing computational design as constrained optimization over multidimensional space
• Automating constraint derivation using LLMs for coherent design solutions
• Validating generalizable framework across visualization and knitwear domains

Innovation

• Constrained optimization in structured design space
• LLM-based constraint derivation via prompt engineering
• Unified framework for scalable AI design automation