AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how they behave in practice and why many of them fail to be merged. In this paper, we conduct a large-scale study of 33k agent-authored PRs made by five coding agents across GitHub. (RQ1) We first quantitatively characterize merged and not-merged PRs along four broad dimensions: 1) merge outcomes across task types, 2) code changes, 3) CI build results, and 4) review dynamics. We observe that tasks related to documentation, CI, and build update achieve the highest merge success, whereas performance and bug-fix tasks perform the worst. Not-merged PRs tend to involve larger code changes, touch more files, and often do not pass the project’s CI/CD pipeline validation. (RQ2) To further investigate why some agentic PRs are not merged, we qualitatively analyze 600 PRs to derive a hierarchical taxonomy of rejection patterns. This analysis complements the quantitative findings in RQ1 by uncovering rejection reasons not captured by quantitative metrics, including lack of meaningful reviewer engagement, duplicate PRs, unwanted feature implementations, and agent misalignment. Together, our findings highlight key socio-technical and human-AI collaboration factors that are critical to improving the success of future agentic workflows.

In the dynamic landscape of open source software (OSS) development, understanding and addressing incivility within issue discussions is crucial for fostering healthy and productive collaborations. This paper presents a curated dataset of 404 locked GitHub issue discussion threads and 5961 individual comments, collected from 213 OSS projects. We annotated the comments with various categories of incivility using Tone Bearing Discussion Features (TBDFs), and, for each issue thread, we annotated the triggers, targets, and consequences of incivility. We observed that Bitter frustration, Impatience, and Mocking are the most prevalent TBDFs exhibited in our dataset. The most common triggers, targets, and consequences of incivility include Failed use of tool/code or error messages, People, and Discontinued further discussion, respectively. This dataset can serve as a valuable resource for analyzing incivility in OSS and improving automated tools to detect and mitigate such behavior.

The availability of quality information in bug reports that are created daily by software users is key to rapidly fixing software faults. Improving incomplete or deficient bug reports, which are numerous in many popular and actively developed open source software projects, can make software maintenance more effective and improve software quality. In this paper, we propose a system that addresses the problem of bug report incompleteness by automatically posing follow-up questions, intended to elicit answers that add value and provide missing information to a bug report. Our system is based on selecting follow-up questions from a large corpus of already posted follow-up questions on GitHub. To estimate the best follow-up question for a specific deficient bug report we combine two metrics based on: 1) the compatibility of a follow-up question to a specific bug report; and 2) the utility the expected answer to the follow-up question would provide to the deficient bug report. Evaluation of our system, based on a manually annotated held-out data set, indicates improved performance over a set of simple and ablation baselines. A survey of software developers confirms the held-out set evaluation result that about half of the selected follow-up questions are considered valid. The survey also indicates that the valid follow-up questions are useful and can provide new information to a bug report most of the time, and are specific to a bug report some of the time.