<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shankar-2026-learning">
    <titleInfo>
        <title>Learning Shortcut Models for Efficient Recursive Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shiv</namePart>
        <namePart type="family">Shankar</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">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="given">Diego</namePart>
            <namePart type="family">Rodriguez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ona</namePart>
            <namePart type="family">de Gibert</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, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-393-7</identifier>
    </relatedItem>
    <abstract>Recursive models that progressively refine latent representations have demonstrated strong performance on a variety of reasoning tasks. However, these models only control whether and when to stop early, not how computation is distributed. In this work, we introduce shortcut reasoning, a framework for distilling recursive latent reasoning into a multiscale jump model that enables flexible test-time compute. We reinterpret recursive reasoning as a latent-time dynamical process and train a student model to predict the effect of multiple reasoning steps at once. To ensure robustness, we augment shortcut transitions with a repair mechanism, where a denoising variant of the base model projects latent states back onto a valid reasoning manifold. We further introduce stepwise improvement supervision, encouraging each shortcut step to increase the likelihood of the correct answer. Experiments on ARC-AGI show that our approach achieves competitive accuracy compared to recursive baselines while requiring fewer sequential updates.</abstract>
    <identifier type="citekey">shankar-2026-learning</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-srw.120/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1351</start>
            <end>1360</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Shortcut Models for Efficient Recursive Reasoning
%A Shankar, Shiv
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%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, United States
%@ 979-8-89176-393-7
%F shankar-2026-learning
%X Recursive models that progressively refine latent representations have demonstrated strong performance on a variety of reasoning tasks. However, these models only control whether and when to stop early, not how computation is distributed. In this work, we introduce shortcut reasoning, a framework for distilling recursive latent reasoning into a multiscale jump model that enables flexible test-time compute. We reinterpret recursive reasoning as a latent-time dynamical process and train a student model to predict the effect of multiple reasoning steps at once. To ensure robustness, we augment shortcut transitions with a repair mechanism, where a denoising variant of the base model projects latent states back onto a valid reasoning manifold. We further introduce stepwise improvement supervision, encouraging each shortcut step to increase the likelihood of the correct answer. Experiments on ARC-AGI show that our approach achieves competitive accuracy compared to recursive baselines while requiring fewer sequential updates.
%U https://aclanthology.org/2026.acl-srw.120/
%P 1351-1360

Markdown (Informal)

[Learning Shortcut Models for Efficient Recursive Reasoning](https://aclanthology.org/2026.acl-srw.120/) (Shankar, ACL 2026)

• Learning Shortcut Models for Efficient Recursive Reasoning (Shankar, ACL 2026)

ACL

• Shiv Shankar. 2026. Learning Shortcut Models for Efficient Recursive Reasoning. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1351–1360, San Diego, California, United States. Association for Computational Linguistics.