.png)
7 hours ago
1
We present some insightful findings from evaluating three different 
LRMs, ranging from 1.5B to 32B across six reasoning benchmarks, including math, code generation, and scientific problem reasoning.
💡 Slow thinking first, then fast thinking, leads to better LRM reasoning.
💡 Slow thinking can bring efficient test-time scaling.
💡 Slow thinking transitioning in high frequency is helpful.
Success Examples
Failure Examples
@article{AlphaOne25,
title={AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time},
author={Zhang, Junyu and Dong, Runpei and Wang, Han and Ning, Xuying and Geng, Haoran and Li, Peihao and He, Xialin and Bai, Yutong and Malik, Jitendra and Gupta, Saurabh and Zhang, Huan},
journal={arXiv preprint arXiv:2505.24863},
year={2025}
}
