EN arXiv·Paper·

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.

Read the original on arxiv.org

English·Web page·opens arxiv.org

Tags

Same week

All of Week 40