English

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models

Sound 2025-09-23 v2 Artificial Intelligence Computation and Language Machine Learning Multimedia Audio and Speech Processing

Abstract

Recent advancements in multimodal reasoning have largely overlooked the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning in audio tasks. 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.

Keywords

Cite

@article{arxiv.2503.02318,
  title  = {Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models},
  author = {Zhifei Xie and Mingbao Lin and Zihang Liu and Pengcheng Wu and Shuicheng Yan and Chunyan Miao},
  journal= {arXiv preprint arXiv:2503.02318},
  year   = {2025}
}

Comments

Technical report, in process

R2 v1 2026-06-28T22:05:52.682Z