# Preprint finds selective problem rewriting improves model accuracy

_Published Saturday, November 14, 2026 at 2:06 AM EST · AI, Science · Latest · Tier 2 — Notable_

A preprint reports that a fixed rule for choosing which problems to rewrite improved model accuracy by +11.0% on selected problems, while blind rewriting lost 5.6% on a similar share. Researchers tested eight models on eight math, logic and code benchmarks using the same solving prompt.

The rewrites exposed subgoals, changed the solving frame or removed surface detail while preserving meaning, constraints and answers. Choosing the best rewrite after seeing results raised accuracy by +27.6% on average, but no single rewrite helped every problem, and mismatched rewrites could hurt.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2611.14997)

---
Canonical: https://techandbusiness.org/newswire/84D8jS81SLjOq4IYZYUpig
Published: 2026-11-14T07:06:02.281Z
Story chronology: 2026-11-14T05:00:00.000Z
Retrieved: 2026-11-15T00:01:48.334Z
Publisher: Tech & Business (techandbusiness.org)