Thinking with Reasoning Skills: Fewer Tokens, More Accuracy

Guangxiang Zhao; Qilong Shi; Xusen Xiao; Xiangzheng Zhang; Tong Yang; Lin Sun

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy

Guangxiang Zhao, Qilong Shi, Xusen Xiao, Xiangzheng Zhang, Tong Yang, Lin Sun

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 <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

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

Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing reasoning from scratch paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment.

Anthology ID:: 2026.acl-industry.154
Volume:: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
Month:: July
Year:: 2026
Address:: San Diego, California, USA
Editors:: Yunyao Li, Georg Rehm, Mei Tu
Venue:: ACL
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 2295–2308
Language:
URL:: https://aclanthology.org/2026.acl-industry.154/
DOI:
Bibkey:
Cite (ACL):: Guangxiang Zhao, Qilong Shi, Xusen Xiao, Xiangzheng Zhang, Tong Yang, and Lin Sun. 2026. Thinking with Reasoning Skills: Fewer Tokens, More Accuracy. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 2295–2308, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):: Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (Zhao et al., ACL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.acl-industry.154.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{zhao-etal-2026-thinking,
    title = "Thinking with Reasoning Skills: Fewer Tokens, More Accuracy",
    author = "Zhao, Guangxiang  and
      Shi, Qilong  and
      Xiao, Xusen  and
      Zhang, Xiangzheng  and
      Yang, Tong  and
      Sun, Lin",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.acl-industry.154/",
    pages = "2295--2308",
    ISBN = "979-8-89176-394-4",
    abstract = "Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing \textit{reasoning from scratch} paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2026-thinking">
    <titleInfo>
        <title>Thinking with Reasoning Skills: Fewer Tokens, More Accuracy</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Guangxiang</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qilong</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xusen</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiangzheng</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tong</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lin</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing reasoning from scratch paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment.</abstract>
    <identifier type="citekey">zhao-etal-2026-thinking</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.154/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>2295</start>
            <end>2308</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
%A Zhao, Guangxiang
%A Shi, Qilong
%A Xiao, Xusen
%A Zhang, Xiangzheng
%A Yang, Tong
%A Sun, Lin
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F zhao-etal-2026-thinking
%X Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing reasoning from scratch paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment.
%U https://aclanthology.org/2026.acl-industry.154/
%P 2295-2308

Download as File

Markdown (Informal)

[Thinking with Reasoning Skills: Fewer Tokens, More Accuracy](https://aclanthology.org/2026.acl-industry.154/) (Zhao et al., ACL 2026)

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (Zhao et al., ACL 2026)

ACL

Guangxiang Zhao, Qilong Shi, Xusen Xiao, Xiangzheng Zhang, Tong Yang, and Lin Sun. 2026. Thinking with Reasoning Skills: Fewer Tokens, More Accuracy. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 2295–2308, San Diego, California, USA. Association for Computational Linguistics.