# SWE-Duel preprint tests coding agents with newly generated defects

_Published Monday, October 12, 2026 at 8:04 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers introduced SWE-Duel, a coding-agent evaluation arena that creates tasks during testing, and reported a tournament involving 11 model-harness participants across 15 repositories in five languages over 1,500 turns. The preprint tackles fixed benchmarks whose tasks can leak into training data or become too easy.

One agent builds a feature and inserts a defect; another reviews the resulting pull request without being told a bug exists. Admission requires feature and repository tests to pass, defect tests to fail, and a fresh agent session to repair the bug.

Tasks authored by the newest version within one model family defeated a fixed-reference solver 42.9% of the time versus 4.0% for older versions, preliminary evidence that difficulty scales with authoring capability.

## Sources

- [cs.CL updates on arXiv.org](https://arxiv.org/abs/2610.12569)

---
Canonical: https://techandbusiness.org/newswire/bTAUK8WrmzPj_O8vQ7V8dF
Published: 2026-10-12T12:04:56.829Z
Story chronology: 2026-10-12T04:00:00.000Z
Retrieved: 2026-10-12T14:05:07.757Z
Publisher: Tech & Business (techandbusiness.org)