@inproceedings{zhifei-etal-2025-audio,
title = "Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models",
author = "Zhifei, Xie and
Lin, Mingbao and
Liu, Zihang and
Wu, Pengcheng and
Yan, Shuicheng and
Miao, Chunyan",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1216/",
pages = "23840--23862",
ISBN = "979-8-89176-332-6",
abstract = "Recent advancements in multimodal reasoning overlook the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning. We meticulously curated a large-scale and diverse multi-task audio dataset with simple annotations. Then, we leverage closed-source models to conduct secondary labeling, QA generation, along with structured COT process. These datasets together form a high-quality reasoning dataset with 1.2 million reasoning-rich samples, which we name CoTA. Following inference scaling principles, we train Audio-Reasoner on CoTA, enabling it to achieve great logical capabilities in audio reasoning. Experiments show state-of-the-art performance across key benchmarks, including MMAU-mini (+25.42{\%}), AIR-Bench chat/foundation (+14.57{\%}/+10.13{\%}), and MELD (+8.01{\%}). Our findings stress the core of structured CoT training in advancing audio reasoning. The model, dataset, and code are open-sourced at [https://github.com/xzf-thu/Audio-Reasoner](https://github.com/xzf-thu/Audio-Reasoner) or [https://huggingface.co/datasets/zhifeixie/Audio-Reasoner-CoTA](https://huggingface.co/datasets/zhifeixie/Audio-Reasoner-CoTA)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhifei-etal-2025-audio">
<titleInfo>
<title>Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xie</namePart>
<namePart type="family">Zhifei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingbao</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuicheng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyan</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Recent advancements in multimodal reasoning overlook the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning. We meticulously curated a large-scale and diverse multi-task audio dataset with simple annotations. Then, we leverage closed-source models to conduct secondary labeling, QA generation, along with structured COT process. These datasets together form a high-quality reasoning dataset with 1.2 million reasoning-rich samples, which we name CoTA. Following inference scaling principles, we train Audio-Reasoner on CoTA, enabling it to achieve great logical capabilities in audio reasoning. Experiments show state-of-the-art performance across key benchmarks, including MMAU-mini (+25.42%), AIR-Bench chat/foundation (+14.57%/+10.13%), and MELD (+8.01%). Our findings stress the core of structured CoT training in advancing audio reasoning. The model, dataset, and code are open-sourced at [https://github.com/xzf-thu/Audio-Reasoner](https://github.com/xzf-thu/Audio-Reasoner) or [https://huggingface.co/datasets/zhifeixie/Audio-Reasoner-CoTA](https://huggingface.co/datasets/zhifeixie/Audio-Reasoner-CoTA).</abstract>
<identifier type="citekey">zhifei-etal-2025-audio</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1216/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>23840</start>
<end>23862</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models
%A Zhifei, Xie
%A Lin, Mingbao
%A Liu, Zihang
%A Wu, Pengcheng
%A Yan, Shuicheng
%A Miao, Chunyan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhifei-etal-2025-audio
%X Recent advancements in multimodal reasoning overlook the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning. We meticulously curated a large-scale and diverse multi-task audio dataset with simple annotations. Then, we leverage closed-source models to conduct secondary labeling, QA generation, along with structured COT process. These datasets together form a high-quality reasoning dataset with 1.2 million reasoning-rich samples, which we name CoTA. Following inference scaling principles, we train Audio-Reasoner on CoTA, enabling it to achieve great logical capabilities in audio reasoning. Experiments show state-of-the-art performance across key benchmarks, including MMAU-mini (+25.42%), AIR-Bench chat/foundation (+14.57%/+10.13%), and MELD (+8.01%). Our findings stress the core of structured CoT training in advancing audio reasoning. The model, dataset, and code are open-sourced at [https://github.com/xzf-thu/Audio-Reasoner](https://github.com/xzf-thu/Audio-Reasoner) or [https://huggingface.co/datasets/zhifeixie/Audio-Reasoner-CoTA](https://huggingface.co/datasets/zhifeixie/Audio-Reasoner-CoTA).
%U https://aclanthology.org/2025.emnlp-main.1216/
%P 23840-23862
Markdown (Informal)
[Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://aclanthology.org/2025.emnlp-main.1216/) (Zhifei et al., EMNLP 2025)
ACL