GHAgentCI 数据集发布：从 GitHub Actions 历史中挖掘编码智能体调用记录
GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories
搞智能体工程的朋友可以看看：研究团队从 6K+ 仓库里挖出 15K+ 条 CI 工作流历史，专门追踪编码智能体在 GitHub Actions 里的用法，抽取工具 cai-miner 开源，准确率验证到 96% 以上。想做智能体与 CI 集成研究或评估的项目直接用得上。
研究团队发布了 GHAgentCI 数据集，从挖掘的 196K+ 个 GitHub 仓库中识别出 6K+ 个仓库的 15K+ 条工作流历史，包含 159K+ 条修订版本和 205K+ 条智能体证据记录，并与工作流触发器和执行约束关联。
配套的开源抽取工具 cai-miner 通过可扩展的规则目录检测智能体相关证据，覆盖 action 引用、shell 命令等信号。人工验证了 576 条分层抽样记录，专用 action 匹配准确率达 96.1%，GitHub Agentic Workflow 匹配达 98.8%，其他证据类型的准确率较低。
探索性分析显示智能体集成正向命令行和 GitHub Agentic Workflow 方式迁移，不同项目声明的安全防护措施差异明显，且被检测到的 agentic 工作流常被移除。数据集可用于编码智能体与 CI 集成的纵向研究。
GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories
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.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：GitHub Actions、cai-miner、编码智能体、CI/CD，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Daniel Ogenrwot, Jorge Gonzalo Delgado Cervantes, Woojoong Kim, John Businge），经 AITOP 多维评分管线结构化提炼。截至目前，全网已有 3 家独立信源对该事件进行交叉印证与跟进报道（含 Latent.Space、IT之家 等），属于近期高关注度行业信号。
