s1: Simple test-time scaling

Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, Tatsunori Hashimoto

Read on arXiv

Type: paper
Venue: arXiv
Year: 2026
Source: arxiv
Access: free
Language: en
Added: 2026-07-17T19:56:36.231920+00:00
Verified: 2026-07-17T19:56:36.231920+00:00

Summary

Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance.

Keywords

paper arxiv cs.cl cs.ai cs.lg

Topics

Computer Science