分析3.3万份代码提交，揭示AI协作如何提升开源开发效率
Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen
- 基于vLLM和SGLang仓库的纵向数据，追踪7项工程指标变化
- 代码提交量飙升21倍（vLLM）与17.9倍（SGLang），主要由人类开发者驱动
- 评论密度提升4倍以上，体现人机协作加深，适合关注AI辅助开发的研究者
随着AI编程助手和自主代理式开发系统的快速应用，开源软件工程的节奏与结构发生了显著变化。然而，团队层面的长期实证研究仍较缺乏。本研究对vLLM（2023年2月–2026年6月；18,290个合并的Pull Request）与SGLang（2024年1月–2026年6月；14,938个合并的PR）两个高速发展的AI基础设施仓库进行了描述性纵向分析，考察了7项工程指标：代码提交吞吐量、周期时间、贡献者多样性、评论密度、合并率、新作者参与度及PR大小。研究将开发阶段划分为四个时期，对应AI辅助开发的重大变革。结果显示，两项目均出现开发速度显著提升，人机协作信号增强。其中，vLLM的提交量增长21倍，SGLang增长17.9倍，而机器人撰写的PR占比不足0.2%，表明增长主要源于人类开发者。最新阶段，vLLM中位周期时间为1.04天，P90为16.8天；SGLang中位为0.62天，P90为14.3天。每月独立作者数持续上升，表明参与范围扩大。评论密度在vLLM中提升4.2倍，SGLang中提升3.8倍，其中机器人评论贡献了约15%-20%的增量。相比之下，PR大小在各阶段保持相对稳定。总体而言，AI辅助开发与更高的产出效率、更广泛的参与者以及更强的人机协作信号相关。
原文摘要 · Abstract (English)
The rapid adoption of AI coding assistants and autonomous agentic development systems has coincided with major changes in the pace and structure of open-source software engineering. Yet empirical longitudinal evidence of these changes at the team level remains limited. We present a descriptive longitudinal analysis of seven engineering metrics: pull request (PR) throughput, cycle time, contributor diversity, PR comment density, merge rate, new-author participation, and PR size. Metrics were computed from all merged PRs in two high-velocity AI infrastructure repositories, vLLM (February 2023-June 2026; 18,290 PRs) and SGLang (January 2024-June 2026; 14,938 PRs). We segment development into four eras aligned with major changes in AI-assisted software development and examine human- and bot-authored activities. Both projects show substantial increases in development velocity and AI-developer collaboration signals. PR throughput increased 21x in vLLM and 17.9x in SGLang, while bot-authored PRs accounted for less than 0.2% of this growth, indicating that the increase was overwhelmingly human-driven. In the latest era, median cycle time was 1.04 days for vLLM and 0.62 days for SGLang, while P90 cycle times reached 16.8 and 14.3 days, respectively. Monthly unique authors increased steadily in both projects, suggesting broader contributor participation. PR comment density increased 4.2x in vLLM and 3.8x in SGLang, with bot comments contributing an estimated 15-20% of the increase. In contrast, PR size remained relatively stable across eras. Overall, AI-assisted development is associated with higher throughput, broader contributor participation, and increased AI-developer collaboration signals in high-velocity open-source software development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。