Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

Xiang He, Chenxing Li, Jinting Wang, Yan Rong, Tianxin Xie, Wenfu Wang, Li Liu, Dong YuarXiv 2026 · DOI

BibTeX
@misc{he2026audio,
  author = {Xiang He and Chenxing Li and Jinting Wang and Yan Rong and Tianxin Xie and Wenfu Wang and Li Liu and Dong Yu},
  title = {{Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models}},
  year = {2026},
  doi = {10.48550/arxiv.2604.18187},
}

Loading related content...

Figure