# PreSTO preprint reports faster sampling for language-model reasoning

_Published Monday, October 12, 2026 at 9:04 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report that PreSTO speeds up a sampling method used to improve language-model reasoning while preserving its underlying acceptance rules. Across seven datasets and five base models, the preprint reports median speedups of 1.71× for PowerMH, 1.91× for EntropyCut and 2.33× for MultiTryMH.

PreSTO batches possible future proposals, then follows the sequence selected by the original sampler. For the first two methods, it used a median of 3.9× fewer model calls, with each call taking 2.1× longer.

## Sources

- [cs.CL updates on arXiv.org](https://arxiv.org/abs/2610.13171)

---
Canonical: https://techandbusiness.org/newswire/XTEFLR6HSsLNKgJHc1CtOD
Published: 2026-10-12T13:04:36.833Z
Story chronology: 2026-10-12T04:00:00.000Z
Retrieved: 2026-10-12T16:38:46.962Z
Publisher: Tech & Business (techandbusiness.org)