EUVIMEDEUVIMED entdecken
Crossref

Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning

Shu Wu, Chenxing Li, Wenfu Wang, Hao Zhang, Hualei Wang, Meng Yu, Dong Yu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 33962-33970

DOI: 10.1609/aaai.v40i40.40689 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shu Wu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning utilizing rule-based rewards. However, the explicit reasoning process has not yet yielded substantial benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of achieving human-level auditory-language reasoning. To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs through improved adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that assist the model in distinguishing between valid and flawed reasoning paths during training. Experimental results demonstrate that Audio-Thinker models outperform existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

Zitieren

APA

Wu, S., Li, C., Wang, W., Zhang, H., Wang, H., Yu, M., & Yu, D. (2026). Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 33962-33970. https://doi.org/10.1609/aaai.v40i40.40689

Vancouver

Wu S, Li C, Wang W, Zhang H, Wang H, Yu M, et al. Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):33962-33970. doi:10.1609/aaai.v40i40.40689

BibTeX
@article{Wu2026,
  author = {Wu, Shu and Li, Chenxing and Wang, Wenfu and Zhang, Hao and Wang, Hualei and Yu, Meng and Yu, Dong},
  title = {Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {40},
  pages = {33962--33970},
  doi = {10.1609/aaai.v40i40.40689}
}
Kostenlos starten →