# Preprint reports iterative framework lifts coding-agent benchmark results

_Wednesday, September 2, 2026 at 12:00 AM EDT · AI, Science · Latest · Tier 2 — Notable_

A preprint describes Harness-of-Harness, a framework that organizes coding-agent harnesses into iterative planning, coding and testing loops intended to improve autonomous software development. The authors report average relative gains of 52.25 percent, with a maximum gain of 82.86 percent after three iterations, across GameCraft-Bench, FrontierSWE and ProgramBench for three harness-model pairs. They also describe a deployment of more than 70 iterations that produced a playable first-person-shooter game with implemented mechanics, visuals and audio.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2609.01481)

---
Canonical: https://techandbusiness.org/newswire/G3Eq8oAukkl4uVBlkloJT4
Retrieved: 2026-09-02T10:37:34.101Z
Publisher: Tech & Business (techandbusiness.org)