A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning

Yixin Ji (纪一心); Juntao Li; Yang Xiang; Hai Ye; Kaixin Wu; Kai Yao; Jia Xu; Linjian Mo; Min Zhang

doi:10.1162/coli.a.629

A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning

Yixin Ji, Juntao Li, Yang Xiang, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo, Min Zhang

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model’s potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model’s reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.1

Anthology ID:: 2026.cl-3.10
Volume:: Computational Linguistics, Volume 52, Issue 3 - September 2026
Month:: September
Year:: 2026
Address:: Cambridge, MA
Venue:: CL
SIG:
Publisher:: MIT Press
Note:
Pages:: 1253–1307
Language:
URL:: https://aclanthology.org/2026.cl-3.10/
DOI:: 10.1162/coli.a.629
Bibkey:
Cite (ACL):: Yixin Ji, Juntao Li, Yang Xiang, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo, and Min Zhang. 2026. A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning. Computational Linguistics, 52(3):1253–1307.
Cite (Informal):: A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning (Ji et al., CL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.cl-3.10.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@article{ji-etal-2026-survey,
    title = "A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning",
    author = "Ji, Yixin  and
      Li, Juntao  and
      Xiang, Yang  and
      Ye, Hai  and
      Wu, Kaixin  and
      Yao, Kai  and
      Xu, Jia  and
      Mo, Linjian  and
      Zhang, Min",
    journal = "Computational Linguistics",
    volume = "52",
    number = "3",
    month = sep,
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2026.cl-3.10/",
    doi = "10.1162/coli.a.629",
    pages = "1253--1307",
    abstract = "The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model{'}s potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model{'}s reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.1"
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ji-etal-2026-survey">
    <titleInfo>
        <title>A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yixin</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Juntao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Xiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hai</namePart>
        <namePart type="family">Ye</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kaixin</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai</namePart>
        <namePart type="family">Yao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jia</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Linjian</namePart>
        <namePart type="family">Mo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model’s potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model’s reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.1</abstract>
    <identifier type="citekey">ji-etal-2026-survey</identifier>
    <identifier type="doi">10.1162/coli.a.629</identifier>
    <location>
        <url>https://aclanthology.org/2026.cl-3.10/</url>
    </location>
    <part>
        <date>2026-09</date>
        <detail type="volume"><number>52</number></detail>
        <detail type="issue"><number>3</number></detail>
        <extent unit="page">
            <start>1253</start>
            <end>1307</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Journal Article
%T A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning
%A Ji, Yixin
%A Li, Juntao
%A Xiang, Yang
%A Ye, Hai
%A Wu, Kaixin
%A Yao, Kai
%A Xu, Jia
%A Mo, Linjian
%A Zhang, Min
%J Computational Linguistics
%D 2026
%8 September
%V 52
%N 3
%I MIT Press
%C Cambridge, MA
%F ji-etal-2026-survey
%X The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model’s potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model’s reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.1
%R 10.1162/coli.a.629
%U https://aclanthology.org/2026.cl-3.10/
%U https://doi.org/10.1162/coli.a.629
%P 1253-1307

Download as File

Markdown (Informal)

[A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning](https://aclanthology.org/2026.cl-3.10/) (Ji et al., CL 2026)

A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning (Ji et al., CL 2026)

ACL

Yixin Ji, Juntao Li, Yang Xiang, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo, and Min Zhang. 2026. A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning. Computational Linguistics, 52(3):1253–1307.