AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub
- ID: 926ad5b3
- 原文链接: https://arxiv.org/abs/2604.03551
- PDF: https://arxiv.org/pdf/2604.03551v2
- 作者: Daniel Ogenrwot, John Businge
- 日期: 2026-04-04
- 更新: 2026-05-12
- 分类: coding
- 来源类型: paper
- 标签: coding-agent, merge-conflict, dataset, empirical-study, github
- 质量评分: 4/5
- 抓取时间: 2026-07-30T04:18:47Z
中文导读
从 59K+ 仓库收集 142K+ AI coding agent 提交的 PR，经确定性合并模拟后处理 107K+发现 29K+ PR 存在合并冲突，冲突率 27.67%，提取出 336K+ 细粒度冲突区域表明 AI 生成贡献的合并冲突既频繁又常较大，且不同 agent 间差异明显
为什么值得关注
27.67% 的 AI agent PR 有合并冲突：AgenticFlict 是首个大规模 AI coding agent 合并冲突数据集
- arXiv comment: Accepted at the 3rd ACM International Conference on AI-Powered Software (AIware 2026)
关键信息
- 论文标题：AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub
- 作者：Daniel Ogenrwot, John Businge
- arXiv：https://arxiv.org/abs/2604.03551
- 发布时间：2026-04-04
- arXiv 分类：cs.SE, cs.AI, cs.HC
- 关联标签：coding-agent, merge-conflict, dataset, empirical-study, github
English Abstract
Software Engineering 3.0 marks a paradigm shift in software development, in which AI coding agents are no longer just assistive tools but active contributors. While prior empirical studies have examined productivity gains and acceptance patterns in AI-assisted development, the challenges associated with integrating agent-generated contributions remain less understood. In particular, merge conflicts, a fundamental aspect of collaborative software development, remain underexplored in this context. In this paper, we present AgenticFlict, a large-scale dataset of textual merge conflicts in AI coding agent pull requests (Agentic PRs). The dataset comprises 142K+ Agentic PRs collected from 59K+ repositories, of which 107K+ are successfully processed through deterministic merge simulation. Our pipeline identifies 29K+ PRs exhibiting merge conflicts, yielding a conflict rate of 27.67%, and extracts 336K+ fine-grained conflict regions across these instances. Our preliminary exploratory analysis indicates that merge conflicts are both frequent and often substantial in AI-generated contributions, with noticeable variation across agents, emphasizing the need to better understand and manage integration challenges in AI-assisted software development. The dataset, code and supplementary materials are available in zenodo: https://doi.org/10.5281/zenodo.19396916.
English Summary
AgenticFlict is a large-scale dataset of textual merge conflicts in AI coding agent pull requests (Agentic PRs). Built from 142K+ Agentic PRs collected from 59K+ repositories, with 107K+ processed through deterministic merge simulation. The pipeline identifies 29K+ PRs exhibiting merge conflicts, yielding a conflict rate of 27.67%, and extracts 336K+ fine-grained conflict regions. Analysis shows merge conflicts are both frequent and often substantial in AI-generated contributions, with noticeable variation across agents, emphasizing the need to better manage integration challenges in AI-assisted development.
Obsidian Notes
- 内容由
opencli arxiv paper拉取 arXiv 元数据与摘要生成。 - 中文导读与价值判断均锚定在条目已有摘要、论文摘要、作者、日期与分类信息上；未补充论文摘要之外的实验细节。