---
id: "lib-2026-09-29-merged-not-measured-an-empirical-study-of"
type: "library"
title: "Merged, Not Measured: An Empirical Study of Performance Issues Fixed by Coding Agents"
lang: "EN"
org: "arXiv"
source_type: "Paper"
date: "2026-09-29"
week: "2026-W40"
url: "https://nosov.ai/library/lib-2026-09-29-merged-not-measured-an-empirical-study-of/"
original_url: "https://arxiv.org/abs/2609.37985"
tags: ["ai technology", "coding agents", "code review"]
frames: ["verification-capacity"]
---

# Merged, Not Measured: An Empirical Study of Performance Issues Fixed by Coding Agents

## English summary

1,262 agent perf fixes from 71,677 AIDev PRs: 57% merged; of 30 re-executed merged fixes only 18 delivered, 9 no gain or regressed; acceptance tracks agent track record in repo (31-37% to 70%), not evidence.

Original: https://arxiv.org/abs/2609.37985