Metraipolis › archive › dc_7a4cfe7ee0fa
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… — arXiv:2608.13884
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13884
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:21:10.848Z
- SHA-256 of the archived text
9f2339db4c94f9c30ab2483bd3e870ae51299cebddfcf3ae341530c434718b87- Stable URL of this page
https://metraipolis.com/documento/dc_7a4cfe7ee0fa
How to cite
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… — arXiv:2608.13884 — arXiv (en), https://arxiv.org/abs/2608.13884 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a4cfe7ee0fa (Metraipolis archive dc_7a4cfe7ee0fa, sha256 9f2339db4c94f9c30ab2483bd3e870ae51299cebddfcf3ae341530c434718b87)
BibTeX
@misc{dc7a4cfe7ee0fa,
title = {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… — arXiv:2608.13884},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13884},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a4cfe7ee0fa; sha256 9f2339db4c94f9c30ab2483bd3e870ae51299cebddfcf3ae341530c434718b87},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13884. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.13884 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T02:02:02.879Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).