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

Spanish

Los agentes de codificación de IA ahora contribuyen a los repositorios de software a escala, sin embargo sus prácticas de documentación siguen sin caracterizar. Analizamos las solicitudes de retiro generadas por IA de 29.669 repositorios en el conjunto de datos de AIDev, midiendo el intercambio de documentación: si las modificaciones de archivos de código se acompañan de una actualización de archivos de documentación en el mismo PR. Descubrimos que el 63.2% de los PRs de IA cambian de código sin actualizar ninguna documentación. Esto varía considerablemente según el tipo de tarea: el 55.2% para las características y el 77.5% para la refacción. Los archivos de código no documentados son seguidos de una corrección al mismo archivo de 8.6 a 11.7% más a menudo que los archivos documentados en ventanas de 30 a

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)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27381, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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