@inproceedings{zhang-etal-2025-alphaone,
title = "{A}lpha{O}ne: 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",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.570/",
doi = "10.18653/v1/2025.emnlp-main.570",
pages = "11340--11365",
ISBN = "979-8-89176-332-6",
abstract = "This paper presents AlphaOne ($\alpha1$), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. $\alpha1$ first introduces $\alpha$ moment, which represents the scaled thinking phase with a universal parameter $\alpha$.Within this scaled pre-$\alpha$ moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the $\alpha$ moment, $\alpha1$ deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoning and efficient answer generation. This approach unifies and generalizes existing monotonic scaling methods by enabling flexible and dense slow-to-fast reasoning modulation. Extensive empirical studies on various challenging benchmarks across mathematical, coding, and scientific domains demonstrate $\alpha1${`}s superior reasoning capability and efficiency. Project page: https://alphaone-project.github.io/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-alphaone">
<titleInfo>
<title>AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runpei</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuying</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peihao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xialin</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jitendra</namePart>
<namePart type="family">Malik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurabh</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>This paper presents AlphaOne (α1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. α1 first introduces α moment, which represents the scaled thinking phase with a universal parameter α.Within this scaled pre-α moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the α moment, α1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoning and efficient answer generation. This approach unifies and generalizes existing monotonic scaling methods by enabling flexible and dense slow-to-fast reasoning modulation. Extensive empirical studies on various challenging benchmarks across mathematical, coding, and scientific domains demonstrate α1‘s superior reasoning capability and efficiency. Project page: https://alphaone-project.github.io/.</abstract>
<identifier type="citekey">zhang-etal-2025-alphaone</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.570</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.570/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>11340</start>
<end>11365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
%A Zhang, Junyu
%A Dong, Runpei
%A Wang, Han
%A Ning, Xuying
%A Geng, Haoran
%A Li, Peihao
%A He, Xialin
%A Bai, Yutong
%A Malik, Jitendra
%A Gupta, Saurabh
%A Zhang, Huan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhang-etal-2025-alphaone
%X This paper presents AlphaOne (α1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. α1 first introduces α moment, which represents the scaled thinking phase with a universal parameter α.Within this scaled pre-α moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the α moment, α1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoning and efficient answer generation. This approach unifies and generalizes existing monotonic scaling methods by enabling flexible and dense slow-to-fast reasoning modulation. Extensive empirical studies on various challenging benchmarks across mathematical, coding, and scientific domains demonstrate α1‘s superior reasoning capability and efficiency. Project page: https://alphaone-project.github.io/.
%R 10.18653/v1/2025.emnlp-main.570
%U https://aclanthology.org/2025.emnlp-main.570/
%U https://doi.org/10.18653/v1/2025.emnlp-main.570
%P 11340-11365
Markdown (Informal)
[AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time](https://aclanthology.org/2025.emnlp-main.570/) (Zhang et al., EMNLP 2025)
ACL
- Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, and Huan Zhang. 2025. AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 11340–11365, Suzhou, China. Association for Computational Linguistics.