发表机构
Portland State University; Clemson University（波特兰州立大学; 克莱姆森大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LLM生成代码增加维护负担的问题，提出PROOF方法，通过结构化规范间接管理代码库，验证语义等价性并同步更新，实验证明其有效性。
AI 中文摘要
LLM生成代码的快速增长增加了软件复杂性，并加重了工程师的维护负担。虽然LLM提供了一种潜在的自动化替代方案，但这种结构复杂性阻碍了它们直接管理代码库的能力。我们引入了原始功能的可证明表示（PROOF），它通过结构化规范间接管理代码库。为了严格通过这些规范实现全生命周期的代码库管理，PROOF将代码库拓扑抽象为层次化的自然语言表示。为了建立绝对信任，系统仅从该规范重建源代码，从而证明语义等价性。这一经过验证的基础驱动维护请求，执行代码修改，同时同步更新自身以防止语义漂移。在真实世界代码库上的实验证实了这些规范的有效性。
英文摘要
The rapid growth of LLM-generated code increases software complexity and the maintenance burden on engineers. While LLMs offer a potential automated alternative, this structural complexity hinders their ability to manage codebases directly. We introduce the Provable Representation Of Original Functionality (PROOF), which manages codebases indirectly via structured specifications. To enable full-lifecycle codebase management strictly through these specifications, PROOF abstracts codebase topology into a hierarchical natural-language representation. To establish absolute trust, the system proves semantic equivalence by reconstructing source code exclusively from this specification. This verified foundation drives maintenance requests, executing code modifications while synchronously updating itself to prevent semantic drift. Experiments on real-world repositories confirm the effectiveness of these specifications.
