DIDUP: 面向UI原型设计的动态迭代开发
DIDUP: Dynamic Iterative Development for UI Prototyping
AI总结：
针对现有LLM代码UI原型系统线性瀑布式流程难应对变更的问题，提出遵循迭代螺旋模型的DIDUP系统，通过自适应规划、代码注入、轻量级状态管理三种机制，提升原型开发迭代效率与用户对代码演化的认知。
摘要：
大语言模型（LLM）在代码编写方面表现出色。人机协作中一个极具价值的应用场景是基于代码的UI原型设计，这是一种创建交互式原型的方法，可让用户查看用户界面并与之充分交互。我们对主流LLM代码原型生成系统GPT Pilot开展了形成性研究，发现其一旦启动开发就难以应对变更，导致在故障预防和动态规划方面存在缺陷，工作流程与瀑布模型的线性模式高度相似。我们提出了DIDUP系统，这是一款遵循迭代螺旋模型的基于代码的UI原型设计系统，能够将开发过程中出现的变更与迭代纳入考量。我们为LLM代码原型生成系统提出了三种创新机制：（1）自适应规划：规划需具备动态性，可反映实现过程中的变更；（2）代码注入：系统应编写最少量代码并进行注入而非重写代码，帮助用户更好地建立代码演化的心智模型；（3）轻量级状态管理：简化版的源代码控制功能，让用户可快速回退到不同的可用状态。这些机制共同助力用户快速开发原型并开展迭代。
英文摘要：
Large language models (LLMs) are remarkably good at writing code. A particularly valuable case of human-LLM collaboration is code-based UI prototyping, a method for creating interactive prototypes that allows users to view and fully engage with a user interface. We conduct a formative study of GPT Pilot, a leading LLM-generated code-prototyping system, and find that its inflexibility towards change once development has started leads to weaknesses in failure prevention and dynamic planning; it closely resembles the linear workflow of the waterfall model. We introduce DIDUP, a system for code-based UI prototyping that follows an iterative spiral model, which takes changes and iterations that come up during the development process into account. We propose three novel mechanisms for LLM-generated code-prototyping systems: (1) adaptive planning, where plans should be dynamic and reflect changes during implementation, (2) code injection, where the system should write a minimal amount of code and inject it instead of rewriting code so users have a better mental model of the code evolution, and (3) lightweight state management, a simplified version of source control so users can quickly revert to different working states. Together, this enables users to rapidly develop and iterate on prototypes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
