Trend · preprint, October 23

58% of Copilot PRs had no human step; no merge rate

Sohail and co-authors analyzed 7,581 pull requests opened by the GitHub Copilot agent and found that 58% had no human intervention from start to finish. The study covers only pull requests with a public work log (arXiv 2610.32313, 2026-10-23). The abstract doesn't list the authors' affiliations. In pull requests where a person did step in, the median number of exchanges between person and agent was 2. After the first intervention, the agent ran 20.8 fewer iterations and spent 8.4 fewer minutes than before it. The abstract doesn't say whether those figures are means or medians. Later interventions made little difference. No intervention doesn't mean the work was good, and the abstract gives no merge rate for the 58%. The sample may lean toward open-source projects and can't be extended to private codebases or other agents. Our read: an evaluation that assumes the agent works alone from start to handoff can't measure what the first human intervention changes.

Concept illustration of an open magazine spread: on the left page a laptop with a red screen shows a window of short horizontal bars and a speech bubble, its base lettered GITHUB COPILOT beside a round emblem; on the right page, under large lettering ARXIV, a matching laptop stands beside a person with dark wavy hair, a black top, a lanyard badge, wide brown trousers and white sneakers, who presses an open hand against its screen. A pale pink circle shows behind the right edge of the spread.

Source

This item ran in the brief of Oct 26, 2026, alongside 5 other items.

Cite this item

SecondSource (2026). "58% of Copilot PRs had no human step; no merge rate." https://secondsource.io/en/research/2026-10-26-2/. Accessed access date.