Salvato in:
Dettagli Bibliografici
Autori principali: Li, Longhao, Chen, Hongjie, Li, Zehan, Hu, Qihan, Kang, Jian, Li, Jie, Xie, Lei, Li, Yongxiang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.12527
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910148392386560
author Li, Longhao
Chen, Hongjie
Li, Zehan
Hu, Qihan
Kang, Jian
Li, Jie
Xie, Lei
Li, Yongxiang
author_facet Li, Longhao
Chen, Hongjie
Li, Zehan
Hu, Qihan
Kang, Jian
Li, Jie
Xie, Lei
Li, Yongxiang
contents Recent advances in reasoning models have driven significant progress in text and multimodal domains, yet audio reasoning remains relatively limited. Only a few Large Audio Language Models (LALMs) incorporate explicit Chain-of-Thought (CoT) reasoning, and their capabilities are often inconsistent and insufficient for complex tasks. To bridge this gap, we introduce Audio-Cogito, a fully open-source solution for deep audio reasoning. We develop Cogito-pipe for high-quality audio reasoning data curation, producing 545k reasoning samples that will be released after review. Based on this dataset, we adopt a self-distillation strategy for model fine-tuning. Experiments on the MMAR benchmark, the only audio benchmark evaluating the CoT process, show that our model achieves the best performance among open-source models and matches or surpasses certain closed-source models in specific metrics. Our approach also ranks among the top-tier systems in the Interspeech 2026 Audio Reasoning Challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12527
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models
Li, Longhao
Chen, Hongjie
Li, Zehan
Hu, Qihan
Kang, Jian
Li, Jie
Xie, Lei
Li, Yongxiang
Audio and Speech Processing
Recent advances in reasoning models have driven significant progress in text and multimodal domains, yet audio reasoning remains relatively limited. Only a few Large Audio Language Models (LALMs) incorporate explicit Chain-of-Thought (CoT) reasoning, and their capabilities are often inconsistent and insufficient for complex tasks. To bridge this gap, we introduce Audio-Cogito, a fully open-source solution for deep audio reasoning. We develop Cogito-pipe for high-quality audio reasoning data curation, producing 545k reasoning samples that will be released after review. Based on this dataset, we adopt a self-distillation strategy for model fine-tuning. Experiments on the MMAR benchmark, the only audio benchmark evaluating the CoT process, show that our model achieves the best performance among open-source models and matches or surpasses certain closed-source models in specific metrics. Our approach also ranks among the top-tier systems in the Interspeech 2026 Audio Reasoning Challenge.
title Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models
topic Audio and Speech Processing
url https://arxiv.org/abs/2604.12527