@inproceedings{kumar-etal-2026-polyaudio,
title = "{P}oly{A}udio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts",
author = "Kumar, Sonal and
Ghosh, Sreyan and
Lin, Yueqian and
Sakshi, S and
Seth, Ashish and
Chen, Yiran and
Duraiswami, Ramani and
Manocha, Dinesh",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.2101/",
pages = "42335--42353",
ISBN = "979-8-89176-395-1",
abstract = "Large Audio Language Models have shown impressive performance on single-clip audio language tasks such as automatic speech recognition, captioning, and sound event recognition. Yet, their ability to reason over interleaved multi-audio contexts-where answering a query requires relating information across multiple audio clips-remains limited. We present PolyAudio, a LALM built on Audio Flamingo 3 that targets multi-audio understanding via instruction tuning rather than massive-scale pre-training, and PolyAudio-Instruct, a high-quality instruction-tuning dataset consisting of 1.3M+ QA pairs, spanning over 14 task subsets to empower multi-audio understanding and reasoning. PolyAudio uses an explicit interleaved representation with clip indexing to encourage faithful grounding and reduce ambiguity in multi-clip references. We evaluate PolyAudio on a diverse suite of multi-audio benchmarks alongside standard single-audio tasks. PolyAudio achieves strong performance on multi-audio reasoning, outperforming competitive baselines that are also often limited to reasoning over up-to 2 audio clips, while preserving robust single-clip performance. Overall, our results suggest that precise, academic-scale multi-audio instruction tuning can unlock advanced cross-clip reasoning capabilities, enabling more capable audio-centric assistants."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2026-polyaudio">
<titleInfo>
<title>PolyAudio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sonal</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sreyan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueqian</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="family">Sakshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Seth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiran</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramani</namePart>
<namePart type="family">Duraiswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Manocha</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large Audio Language Models have shown impressive performance on single-clip audio language tasks such as automatic speech recognition, captioning, and sound event recognition. Yet, their ability to reason over interleaved multi-audio contexts-where answering a query requires relating information across multiple audio clips-remains limited. We present PolyAudio, a LALM built on Audio Flamingo 3 that targets multi-audio understanding via instruction tuning rather than massive-scale pre-training, and PolyAudio-Instruct, a high-quality instruction-tuning dataset consisting of 1.3M+ QA pairs, spanning over 14 task subsets to empower multi-audio understanding and reasoning. PolyAudio uses an explicit interleaved representation with clip indexing to encourage faithful grounding and reduce ambiguity in multi-clip references. We evaluate PolyAudio on a diverse suite of multi-audio benchmarks alongside standard single-audio tasks. PolyAudio achieves strong performance on multi-audio reasoning, outperforming competitive baselines that are also often limited to reasoning over up-to 2 audio clips, while preserving robust single-clip performance. Overall, our results suggest that precise, academic-scale multi-audio instruction tuning can unlock advanced cross-clip reasoning capabilities, enabling more capable audio-centric assistants.</abstract>
<identifier type="citekey">kumar-etal-2026-polyaudio</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2101/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>42335</start>
<end>42353</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PolyAudio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts
%A Kumar, Sonal
%A Ghosh, Sreyan
%A Lin, Yueqian
%A Sakshi, S.
%A Seth, Ashish
%A Chen, Yiran
%A Duraiswami, Ramani
%A Manocha, Dinesh
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F kumar-etal-2026-polyaudio
%X Large Audio Language Models have shown impressive performance on single-clip audio language tasks such as automatic speech recognition, captioning, and sound event recognition. Yet, their ability to reason over interleaved multi-audio contexts-where answering a query requires relating information across multiple audio clips-remains limited. We present PolyAudio, a LALM built on Audio Flamingo 3 that targets multi-audio understanding via instruction tuning rather than massive-scale pre-training, and PolyAudio-Instruct, a high-quality instruction-tuning dataset consisting of 1.3M+ QA pairs, spanning over 14 task subsets to empower multi-audio understanding and reasoning. PolyAudio uses an explicit interleaved representation with clip indexing to encourage faithful grounding and reduce ambiguity in multi-clip references. We evaluate PolyAudio on a diverse suite of multi-audio benchmarks alongside standard single-audio tasks. PolyAudio achieves strong performance on multi-audio reasoning, outperforming competitive baselines that are also often limited to reasoning over up-to 2 audio clips, while preserving robust single-clip performance. Overall, our results suggest that precise, academic-scale multi-audio instruction tuning can unlock advanced cross-clip reasoning capabilities, enabling more capable audio-centric assistants.
%U https://aclanthology.org/2026.findings-acl.2101/
%P 42335-42353
Markdown (Informal)
[PolyAudio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts](https://aclanthology.org/2026.findings-acl.2101/) (Kumar et al., Findings 2026)
ACL
- Sonal Kumar, Sreyan Ghosh, Yueqian Lin, S Sakshi, Ashish Seth, Yiran Chen, Ramani Duraiswami, and Dinesh Manocha. 2026. PolyAudio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts. In Findings of the Association for Computational Linguistics: ACL 2026, pages 42335–42353, San Diego, California, United States. Association for Computational Linguistics.