DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming

2024-10-01

arXiv.org

AI Summary

Existing exploratory programming tools prioritize code generation over design decision-making, limiting the diversity and complexity of prototypes. This paper introduces DynEx, a design-matrix-driven dynamic code synthesis framework that models the design space via structured prompt engineering, enabling systematic exploration of alternatives before generating frontend prototypes. DynEx employs modular, stepwise LLM-based code generation coupled with interactive feedback mechanisms to support “testable and approvable” iterative development, thereby bridging the gap between design thinking and LLM-powered implementation. To our knowledge, this is the first work to establish a design-matrix-guided paradigm for structured design-space exploration. A user study demonstrates that DynEx significantly outperforms the Claude Artifact baseline, increasing design exploration breadth by +42% and depth by +37%. Expert users successfully constructed frontend prototypes exhibiting greater complexity and diversity.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent advancements in large language models have significantly expedited the process of generating front-end code. This allows users to rapidly prototype user interfaces and ideate through code, a process known as exploratory programming. However, existing LLM code generation tools focus more on technical implementation details rather than finding the right design given a particular problem. We present DynEx, an LLM-based method for design exploration in accelerated exploratory programming. DynEx introduces a technique to explore the design space through a structured Design Matrix before creating the prototype with a modular, stepwise approach to LLM code generation. Code is generated sequentially, and users can test and approve each step before moving onto the next. A user study of 10 experts found that DynEx increased design exploration and enabled the creation of more complex and varied prototypes compared to a Claude Artifact baseline. We conclude with a discussion of the implications of design exploration for exploratory programming.

Problem

• Exploratory Programming
• Solution Optimization
• Design Complexity

Innovation

• DynEx
• Exploratory Programming
• Large Language Models