@inproceedings{wang-etal-2026-survey-entropy,
title = "A Survey on Entropy Mechanism in Large Reasoning Models",
author = "Wang, Zihan and
Xu, Xingle and
Wang, Hao and
Ye, Yiwen and
Li, Yuchen and
Wang, Linhao and
Tan, Hongze and
Wang, Peidong and
Feng, Shi and
Chen, Guoqing and
Lin, Jinghao and
Wang, Zijing and
Zhang, Yiqun and
Liu, Yongkang and
Yang, Xiaocui and
Yan, Tao and
Yang, Lei and
Wang, Shengzhi and
Wu, Yuhang and
Yu, Ge",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2478/",
pages = "53321--53347",
ISBN = "979-8-89176-462-0",
abstract = "Entropy mechanism emerges as a key organizing principle for understanding and improving Large Reasoning Models (LRMs). This survey examines how entropy shapes both their training and inference behavior. On the training side, we take a mathematical perspective: casting existing RL-based reasoning algorithms into a unified objective and using this formulation to derive an entropy-centric decomposition of methods, clarifying how different approaches adjust exploration{--}exploitation ``knobs''. On the inference side, based on the characteristic of LRM that trading increased inference tokens yields better performance, we summarize methods that leverage entropy to enhance inference performance or reduce uncertainty. Finally, we discuss open challenges and future directions of entropy-driven research for LRMs. Our repository is available on https://anonymous.4open.science/r/Awesome{\_}LRM{\_}with{\_}Entropy-0503."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-survey-entropy">
<titleInfo>
<title>A Survey on Entropy Mechanism in Large Reasoning Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingle</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwen</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linhao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongze</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peidong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoqing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghao</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongkang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaocui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengzhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Entropy mechanism emerges as a key organizing principle for understanding and improving Large Reasoning Models (LRMs). This survey examines how entropy shapes both their training and inference behavior. On the training side, we take a mathematical perspective: casting existing RL-based reasoning algorithms into a unified objective and using this formulation to derive an entropy-centric decomposition of methods, clarifying how different approaches adjust exploration–exploitation “knobs”. On the inference side, based on the characteristic of LRM that trading increased inference tokens yields better performance, we summarize methods that leverage entropy to enhance inference performance or reduce uncertainty. Finally, we discuss open challenges and future directions of entropy-driven research for LRMs. Our repository is available on https://anonymous.4open.science/r/Awesome_LRM_with_Entropy-0503.</abstract>
<identifier type="citekey">wang-etal-2026-survey-entropy</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2478/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>53321</start>
<end>53347</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey on Entropy Mechanism in Large Reasoning Models
%A Wang, Zihan
%A Xu, Xingle
%A Wang, Hao
%A Ye, Yiwen
%A Li, Yuchen
%A Wang, Linhao
%A Tan, Hongze
%A Wang, Peidong
%A Feng, Shi
%A Chen, Guoqing
%A Lin, Jinghao
%A Wang, Zijing
%A Zhang, Yiqun
%A Liu, Yongkang
%A Yang, Xiaocui
%A Yan, Tao
%A Yang, Lei
%A Wang, Shengzhi
%A Wu, Yuhang
%A Yu, Ge
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F wang-etal-2026-survey-entropy
%X Entropy mechanism emerges as a key organizing principle for understanding and improving Large Reasoning Models (LRMs). This survey examines how entropy shapes both their training and inference behavior. On the training side, we take a mathematical perspective: casting existing RL-based reasoning algorithms into a unified objective and using this formulation to derive an entropy-centric decomposition of methods, clarifying how different approaches adjust exploration–exploitation “knobs”. On the inference side, based on the characteristic of LRM that trading increased inference tokens yields better performance, we summarize methods that leverage entropy to enhance inference performance or reduce uncertainty. Finally, we discuss open challenges and future directions of entropy-driven research for LRMs. Our repository is available on https://anonymous.4open.science/r/Awesome_LRM_with_Entropy-0503.
%U https://aclanthology.org/2026.findings-emnlp.2478/
%P 53321-53347
Markdown (Informal)
[A Survey on Entropy Mechanism in Large Reasoning Models](https://aclanthology.org/2026.findings-emnlp.2478/) (Wang et al., Findings 2026)
ACL
- Zihan Wang, Xingle Xu, Hao Wang, Yiwen Ye, Yuchen Li, Linhao Wang, Hongze Tan, Peidong Wang, Shi Feng, Guoqing Chen, Jinghao Lin, Zijing Wang, Yiqun Zhang, Yongkang Liu, Xiaocui Yang, Tao Yan, Lei Yang, Shengzhi Wang, Yuhang Wu, and Ge Yu. 2026. A Survey on Entropy Mechanism in Large Reasoning Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 53321–53347, Budapest, Hungary. Association for Computational Linguistics.