@inproceedings{jang-etal-2026-reasoning,
title = "Reasoning Model is Stubborn: Diagnosing and Mitigating Reasoning Rigidity in Large Language Models",
author = "Jang, Doohyuk and
Kim, Yoonjeon and
Park, Chanjae and
Ryu, Hyun and
Yang, Eunho",
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.7/",
pages = "115--146",
ISBN = "979-8-89176-462-0",
abstract = "Large reasoning models have demonstrated remarkable proficiency in various tasks. However, we observe that they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term reasoning rigidity. Despite explicit instructions from users, these models often override clearly stated conditions and default to habitual reasoning, leading to incorrect conclusions. This behavior presents significant challenges, not only in reasoning-intensive domains but also in realistic settings. To systematically investigate reasoning rigidity, a behavior unexplored in prior work, we introduce a dataset, ReasoningTrap, consisting of math problems, puzzles, and agentic tasks designed to diagnose reasoning rigidity. Using this dataset, we identify patterns that occur when models default to ingrained reasoning, and suggest inference-level and GRPO-based post-training remedies. Our diagnostic set and evaluation code are available at the project page to facilitate future research on mitigating reasoning rigidity in language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2026-reasoning">
<titleInfo>
<title>Reasoning Model is Stubborn: Diagnosing and Mitigating Reasoning Rigidity in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Doohyuk</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonjeon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanjae</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyun</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunho</namePart>
<namePart type="family">Yang</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>Large reasoning models have demonstrated remarkable proficiency in various tasks. However, we observe that they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term reasoning rigidity. Despite explicit instructions from users, these models often override clearly stated conditions and default to habitual reasoning, leading to incorrect conclusions. This behavior presents significant challenges, not only in reasoning-intensive domains but also in realistic settings. To systematically investigate reasoning rigidity, a behavior unexplored in prior work, we introduce a dataset, ReasoningTrap, consisting of math problems, puzzles, and agentic tasks designed to diagnose reasoning rigidity. Using this dataset, we identify patterns that occur when models default to ingrained reasoning, and suggest inference-level and GRPO-based post-training remedies. Our diagnostic set and evaluation code are available at the project page to facilitate future research on mitigating reasoning rigidity in language models.</abstract>
<identifier type="citekey">jang-etal-2026-reasoning</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.7/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>115</start>
<end>146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reasoning Model is Stubborn: Diagnosing and Mitigating Reasoning Rigidity in Large Language Models
%A Jang, Doohyuk
%A Kim, Yoonjeon
%A Park, Chanjae
%A Ryu, Hyun
%A Yang, Eunho
%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 jang-etal-2026-reasoning
%X Large reasoning models have demonstrated remarkable proficiency in various tasks. However, we observe that they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term reasoning rigidity. Despite explicit instructions from users, these models often override clearly stated conditions and default to habitual reasoning, leading to incorrect conclusions. This behavior presents significant challenges, not only in reasoning-intensive domains but also in realistic settings. To systematically investigate reasoning rigidity, a behavior unexplored in prior work, we introduce a dataset, ReasoningTrap, consisting of math problems, puzzles, and agentic tasks designed to diagnose reasoning rigidity. Using this dataset, we identify patterns that occur when models default to ingrained reasoning, and suggest inference-level and GRPO-based post-training remedies. Our diagnostic set and evaluation code are available at the project page to facilitate future research on mitigating reasoning rigidity in language models.
%U https://aclanthology.org/2026.findings-emnlp.7/
%P 115-146
Markdown (Informal)
[Reasoning Model is Stubborn: Diagnosing and Mitigating Reasoning Rigidity in Large Language Models](https://aclanthology.org/2026.findings-emnlp.7/) (Jang et al., Findings 2026)
ACL