AI辅助开发是否导致软件同质化？代码相似性、质量与演化的实证研究
原标题：Does AI-Assisted Development Homogenize Software? An Empirical Study of Code Similarity, Quality, and Evolution
AI 摘要
该研究基于 Software Heritage 快照，对 50 个长期维护的 Java 和 Python 开源项目在三个时期（前 LLM 时代、可能 LLM 辅助时代、检测到的智能体开发时代）的代码相似性、质量和演化进行实证分析。结果显示，Java 在 LLM 和智能体时代的语义与语法相似性反而显著下降，Python 无显著差异；软件质量总体稳定，智能体时代的代码异味和 SQALE 指数密度显著更低；结构增长普遍放缓，但 Java 的开发活动（提交和新增行数）适度增加。研究结论挑战了 LLM 和智能体辅助开发必然导致代码同质化、质量下降或增长加速的假设。
正文节选
Does AI-Assisted Development Homogenize Software? An Empirical Study of Code Similarity, Quality, and Evolution Abstract AI-assisted software development is evolving from interactive LLM assistance toward agentic systems that autonomously perform software engineering tasks, yet the effects of this shift remain insufficiently understood. We present an empirical study of 50 long-lived Java and Python open-source projects across three eras: pre-LLM, potentially LLM-assisted, and detected agentic de