智能体编码时代人机协作的工程信号：对vLLM和SGLang中33228个拉取请求的纵向分析及其对生物医学智能体和生物信息学流程开发的启示
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
浏览论文内容
中文总结 AI 辅助
该研究对vLLM和SGLang的33228个拉取请求进行纵向分析，发现AI辅助开发提升了开源软件的吞吐量、贡献者参与度及人机协作信号，且增长主要由人类驱动，为生物医学智能体开发提供启示。
中文摘要 AI 辅助
AI编程助手和自主智能体开发系统的快速普及，与开源软件工程的节奏和结构发生重大变化同步出现。然而，关于团队层面这些变化的实证纵向证据仍然有限。我们对七个工程指标进行描述性纵向分析：拉取请求（PR）吞吐量、周期时间、贡献者多样性、PR评论密度、合并率、新作者参与度和PR规模。这些指标从两个高速度AI基础设施仓库中所有已合并的PR计算得出：vLLM（2023年2月-2026年6月；18290个PR）和SGLang（2024年1月-2026年6月；14938个PR）。我们将开发阶段划分为四个与AI辅助软件开发重大变化相对应的时代，并研究人类和机器人发起的活动。两个项目均显示出开发速度和AI-开发者协作信号的大幅提升：vLLM的PR吞吐量增长21倍，SGLang增长17.9倍，而机器人发起的PR在该增长中占比不到0.2%，表明增长绝大多数由人类驱动。在最新时代，vLLM的中位周期时间为1.04天，SGLang为0.62天，而P90周期时间分别达到16.8天和14.3天。两个项目的月度唯一作者数量稳步增长，表明贡献者参与范围扩大。PR评论密度在vLLM中增长4.2倍，在SGLang中增长3.8倍，其中机器人评论贡献了估计15%-20%的增长。相比之下，PR规模在各个时代保持相对稳定。总体而言，在高速度开源软件开发中，AI辅助开发与更高的吞吐量、更广泛的贡献者参与以及增强的AI-开发者协作信号相关。
英文摘要
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.
发表机构
- Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。
