Research

Paper

AI LLM February 27, 2026

Novice Developers Produce Larger Review Overhead for Project Maintainers while Vibe Coding

Authors

Syed Ammar Asdaque, Imran Haider, Muhammad Umar Malik, Maryam Abdul Ghafoor, Abdul Ali Bangash

Abstract

AI coding agents allow software developers to generate code quickly, which raises a practical question for project managers and open source maintainers: can vibe coders with less development experience substitute for expert developers? To explore whether developer experience still matters in AI-assisted development, we study $22,953$ Pull Requests (PRs) from $1,719$ vibe coders in the GitHub repositories of the AIDev dataset. We split vibe coders into lower experience vibe coders ($\mathit{Exp}_{Low}$) and higher experience vibe coders ($\mathit{Exp}_{High}$) and compare contribution magnitude and PR acceptance rates across PR categories. We find that $\mathit{Exp}_{Low}$ submits PRs with larger volume ($2.15\times$ more commits and $1.47\times$ more files changed) than $\mathit{Exp}_{High}$. Moreover, $\mathit{Exp}_{Low}$ PRs, when compared to $\mathit{Exp}_{High}$, receive $4.52\times$ more review comments, and have $31\%$ lower acceptance rates, and remain open $5.16\times$ longer before resolution. Our results indicate that low-experienced vibe coders focus on generating more code while shifting verification burden onto reviewers. For practice, project managers may not be able to safely replace experienced developers with low-experience vibe coders without increasing review capacity. Development teams should therefore combine targeted training for novices with adaptive PR review cycles.

Metadata

arXiv ID: 2602.23905
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.23905v1</id>\n    <title>Novice Developers Produce Larger Review Overhead for Project Maintainers while Vibe Coding</title>\n    <updated>2026-02-27T10:55:43Z</updated>\n    <link href='https://arxiv.org/abs/2602.23905v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.23905v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>AI coding agents allow software developers to generate code quickly, which raises a practical question for project managers and open source maintainers: can vibe coders with less development experience substitute for expert developers? To explore whether developer experience still matters in AI-assisted development, we study $22,953$ Pull Requests (PRs) from $1,719$ vibe coders in the GitHub repositories of the AIDev dataset. We split vibe coders into lower experience vibe coders ($\\mathit{Exp}_{Low}$) and higher experience vibe coders ($\\mathit{Exp}_{High}$) and compare contribution magnitude and PR acceptance rates across PR categories. We find that $\\mathit{Exp}_{Low}$ submits PRs with larger volume ($2.15\\times$ more commits and $1.47\\times$ more files changed) than $\\mathit{Exp}_{High}$. Moreover, $\\mathit{Exp}_{Low}$ PRs, when compared to $\\mathit{Exp}_{High}$, receive $4.52\\times$ more review comments, and have $31\\%$ lower acceptance rates, and remain open $5.16\\times$ longer before resolution. Our results indicate that low-experienced vibe coders focus on generating more code while shifting verification burden onto reviewers. For practice, project managers may not be able to safely replace experienced developers with low-experience vibe coders without increasing review capacity. Development teams should therefore combine targeted training for novices with adaptive PR review cycles.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <published>2026-02-27T10:55:43Z</published>\n    <arxiv:comment>Accepted to MSR 2026 Mining Challenge</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Syed Ammar Asdaque</name>\n    </author>\n    <author>\n      <name>Imran Haider</name>\n    </author>\n    <author>\n      <name>Muhammad Umar Malik</name>\n    </author>\n    <author>\n      <name>Maryam Abdul Ghafoor</name>\n    </author>\n    <author>\n      <name>Abdul Ali Bangash</name>\n    </author>\n  </entry>"
}