# Interactive testing improves coding agents' application repairs in preprint

_Published Monday, October 26, 2026 at 2:06 AM EDT · Science, AI · Latest · Tier 2 — Notable_

Researchers report that coding agents repaired 75.5% of broken application requirements within five attempts when feedback came from agents interacting with the software, compared with 55.4% using code-only feedback. The preprint tests an evaluation method in which computer-use agents operate websites, desktop applications and games to assess their behavior.

The researchers released 6,858 application pairs with human preferences and agent traces, plus 222 applications with human-verified requirement labels. Interactive evaluation improved prediction of human preferences from 65.6% to 69.1% and requirement verification from 77.0% to 81.6%. The method improved alignment with human judgments, but its preference predictions still fell short of matching them consistently.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.17895)

---
Canonical: https://techandbusiness.org/newswire/KIxiOSa3rqH8og3UmuMW_-
Published: 2026-10-26T06:06:06.955Z
Story chronology: 2026-10-26T04:00:00.000Z
Retrieved: 2026-10-26T08:48:25.222Z
Publisher: Tech & Business (techandbusiness.org)