arXiv cs.AI· Daniel Ogenrwot, Jorge Gonzalo Delgado Cervantes, Woojoong Kim, John Businge·· 3 小时前AI 评分34
GHAgentCI：一个编码智能体调用 CI 工作流历史的数据集
GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories
AI 导读
GHAgentCI 是一个编码智能体在 GitHub Actions 中调用的数据集，收录来自 6K+ 个仓库的 15K+ 条工作流历史，含 159K+ 修订和 205K+ 条智能体证据记录。
正文 · 原文
Abstract:Coding agents are increasingly integrated into GitHub Actions to review pull requests, triage issues and modify code. Identifying these integrations is challenging because agentic workflows often resemble ordinary CI files, with evidence appearing in action references, shell commands and workflow conventions. We present GHAgentCI, a dataset of 15K+ workflow histories from 6K+ of 196K+ mined GitHub repositories, comprising 159K+ revisions and 205K+ agent-evidence records linked to workflow triggers and declared execution constraints. Our open-source extractor, cai-miner, detects agent-related evidence using an extensible catalogue. Manual validation of 576 stratified records confirmed 96.1% of dedicated-action matches and 98.8% of GitHub Agentic Workflow matches, with lower rates for other evidence kinds. Exploratory analyses reveal a shift toward command-line and GitHub Agentic Workflow integrations, differences in declared safeguards, and frequent removal of detected agentic workflows. GHAgentCI supports longitudinal studies of coding-agent integration into CI.
| Comments: | 5 pages, 3 figures |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| ACM classes: | K.6.3; I.2.2 |
| Cite as: | arXiv:2611.15522 [cs.SE] |
| (or arXiv:2611.15522v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15522 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Daniel Ogenrwot [view email]
[v1]
Wed, 11 Nov 2026 14:13:33 UTC (128 KB)
来源：arXiv cs.AI · arxiv.org