Newest papers

Documentation Drift in AI-Generated Pull Requests

Will De Michele, Kla Tantithamthavorn · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27381 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

AI编码代理人现在在规模上贡献软件库,但他们的文档实践仍然未被描述。我们分析了AIDev数据集中的2585个库中的29669个AI生成的拉动请求,测量了文档联合交换:是否代码文件的更改伴随着同一PR的文档更新。我们发现,AI PR的63.2%在没有更新任何文档的情况下更改代码。这取决于任务类型:55.2%用于功能和77.5%用于重构。未经文档的代码文件随后对相同文件进行修复的频率比30至90天窗口的文档文件更为频繁8.6到11.7%。原始PR水平比较显示相反,因为文档PR大于3.9倍,因此吸引更多的修复。对大小的曝光进行控制导致了这一结果。文

Machine translation (Meta M2M100); the English original follows.

Abstract

AI coding agents now contribute to software repositories at scale, yet their documentation practices remain uncharacterised. We analyse 29,669 AI-generated pull requests from 2,585 repositories in the AIDev dataset, measuring documentation co-change: whether code-file modifications are accompanied by a documentation-file update in the same PR. We find that 63.2% of AI PRs change code without updating any documentation. This varies sharply by task type: 55.2% for features and 77.5% for refactoring. Undocumented code files are followed by a fix to the same file 8.6 to 11.7% more often than documented files across 30 to 90-day windows. A raw PR-level comparison shows the opposite because documented PRs are 3.9 times larger and therefore attract more fixes. Controlling for size exposure reverses this result. Documented changes also merge faster despite their larger size (median: 40 seconds versus 184 seconds), although merging is largely automated in this dataset. Documentation drift also compounds: within 90 days, a file changed without documentation is later re-documented at roughly half the rate of a file changed with documentation (24% versus 48%). This suggests that documentation debt tends to accumulate rather than be revisited.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Documentation, Merge (version control), Computer science, Internal documentation, Task (project management), Coding (social sciences)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange