从函数到类的测试驱动代码生成规模化：一项实证研究
Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study
AI总结：
本文提出一种测试驱动代码生成框架，通过迭代方法提升类级代码生成的正确性和可靠性。
摘要：
测试驱动开发（TDD）已被采用以通过使用可执行规范来提高基于大语言模型（LLM）的代码生成。然而，现有的TDD风格代码生成研究大多局限于函数级任务，留下类级合成领域未被充分探索，该领域涉及多个方法通过共享状态和调用依赖进行交互。在本文中，我们通过迭代TDD框架将测试驱动代码生成从函数扩展到类。我们的方法首先分析类内方法依赖性以推导可行的生成计划，然后在方法级公共测试下逐步实现每个方法，使用反射式执行反馈和有界的修复迭代。为了支持测试驱动生成和严谨的类级评估，我们构建了ClassEval-TDD，这是ClassEval的清理和标准化变体，具有一致的规范、确定性的测试环境和完整的类级公共测试。我们跨八个LLM进行实证研究，并与最强的直接生成基线（最佳的整体、增量和组合策略）进行比较。我们的类级TDD框架在类级正确性上始终提高了12到26个绝对点，并实现了高达71%完全正确的类，同时仅需要平均少量的修复。这些结果表明，测试驱动生成可以有效扩展到孤立函数之外，并显著提高类级代码生成的可靠性。所有代码和数据均在https://anonymous.4open.science/r/ClassEval-TDD-C4C9/上提供。
英文摘要：
Test-driven development (TDD) has been adopted to improve Large Language Model (LLM)-based code generation by using tests as executable specifications. However, existing TDD-style code generation studies are largely limited to function-level tasks, leaving class-level synthesis where multiple methods interact through shared state and call dependencies underexplored. In this paper, we scale test-driven code generation from functions to classes via an iterative TDD framework. Our approach first analyzes intra-class method dependencies to derive a feasible generation schedule, and then incrementally implements each method under method-level public tests with reflection-style execution feedback and bounded repair iterations. To support test-driven generation and rigorous class-level evaluation, we construct ClassEval-TDD, a cleaned and standardized variant of ClassEval with consistent specifications, deterministic test environments, and complete method-level public tests. We conduct an empirical study across eight LLMs and compare against the strongest direct-generation baseline (the best of holistic, incremental, and compositional strategies). Our class-level TDD framework consistently improves class-level correctness by 12 to 26 absolute points and achieves up to 71% fully correct classes, while requiring only a small number of repairs on average. These results demonstrate that test-driven generation can effectively scale beyond isolated functions and substantially improve class-level code generation reliability. All code and data are available at https://anonymous.4open.science/r/ClassEval-TDD-C4C9/
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。
