arXiv AI

SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty

The paper introduces SWEAR, a framework for audio-language models that uses a five‑dimensional difficulty score to guide reasoning. By learning difficulty signals during fine‑tuning and applying reinforcement learning, SWEAR allocates reasoning effort adaptively across stages. Experiments on MMAU‑test‑mini and MMAR demonstrate that SWEAR boosts accuracy while cutting the number of generated tokens, especially for easier cases.

Hugging Face Trending Papers

Oct 9

SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty

SWEAR is a difficulty‑aware reasoning framework for large audio‑language models that derives five‑dimensional difficulty scores and compressed reasoning traces from offline assessments. It learns these difficulty signals during supervised fine‑tuning and employs reinforcement learning to adapt reasoning allocation across stages, shortening reasoning for easy instances while maintaining performance on hard ones. Experiments on MMAU‑test‑mini and MMAR demonstrate that SWEAR improves accuracy and reduces generated tokens.

llms reinforcement-learning fine-tuning

arXiv AI

Sep 23

Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models

arXiv:2609.23589v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio repr...

By Jiaheng Dong, Xiaofeng Yu, Jean Honorio, Abhirup Ghosh, Hong Jia, Ting Dang

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jun 15

AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models

arXiv:2606. 14591v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning.

By Hui Geng, Yi Su, Han Yin, Tianjiao Wan, Qisheng Xu, Jiaxin Chen, Zijian Gao, Hengzhu Liu, Xie Chen, Kele Xu

llms benchmarks

arXiv AI

Sep 23

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning

arXiv:2603.02266v2 Announce Type: replace-cross Abstract: Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-La...

By Ruixiang Mao, Xiangnan Ma, Dan Chen, Ziming Zhu, Yuan Ge, Aokai Hao, Haishu Zhao, Yifu Huo, Qing Yang, Kaiyan Chang, Xiaoqian Liu, Chenglong Wang, Qiaozhi He, Tong Xiao, Jingbo Zhu

llms reinforcement-learning benchmarks

arXiv AI

Jun 30

ORCA: Open-ended Response Correctness Assessment for Audio Question Answering

arXiv:2512. 09066v2 Announce Type: replace-cross Abstract: Reliable assessment of the abilities of large audio language models (LALMs) is essential to advancing the state of the art.

By \v{S}imon Sedl\'a\v{c}ek, Sara Barahona, Bolaji Yusuf, Laura Herrera-Alarc\'on, Santosh Kesiraju, Cecilia Bola\~nos, Alicia Lozano-Diez, Sathvik Udupa, Fernando L\'opez, Allison Ferner, Ramani Duraiswami, Jan \v{C}ernock\'y

llms nlp benchmarks

Hugging Face Trending Papers

Jul 22

Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning

Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e. g.

llms reinforcement-learning

arXiv AI

Jul 23

Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning

arXiv:2607. 20166v1 Announce Type: cross Abstract: Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.

By Siqian Tong, Xuan Li, Chaozhuo Li, Baolong Bi, Yiwei Wang, Yujun Cai, Shenghua Liu, Chengpeng Hao

llms reinforcement-learning

arXiv Machine Learning

Sep 24

EvoAudio: Recursive Self-Improvement for Audio Understanding

arXiv:2609.27389v1 Announce Type: cross Abstract: Audio language models understand what is said far better than how it sounds. Closing this gap takes more than data. Detailed acoustic annotation is c...

By Yuxiang Wang, Shengbo Cai, Yingda Shen, Ming-Hao Hsu, Qinke Ni, Liqiang Zhang, Teddy Sun, Steve Yevs, Zhizheng Wu

llms reinforcement-learning

arXiv Computation and Language

Sep 21

Enhancing Audio Reasoning via Semantic Summary Prediction

arXiv:2609.20849v1 Announce Type: new Abstract: Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) re...

By Francesco Bonzi, Pooneh Mousavi, Cem Subakan, Mirco Ravanelli

llms rag diffusion nlp

arXiv Machine Learning

Oct 7

AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models

AdaLoop is a lightweight recurrent module that adaptively determines how many latent refinement steps are needed for audio–question pairs, allowing deeper reasoning only when necessary. It shares a transformer block that iterates over the audio representation guided by the question, with a learned halting mechanism that exits the loop once the representation is ready. Adding fewer than 3 % of the base model’s parameters, AdaLoop improves average accuracy by 2.9 to 3.8 points across three distinct models, especially on perception-heavy subtasks.

By Lee Seung-woo, Bowen Qi

llms

arXiv AI

Jun 3

AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following

arXiv:2606. 03116v1 Announce Type: cross Abstract: The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation.

By Haitao Li, Tian Tan, Yuguang Yang, Shan Yang, Xie Chen

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 17

A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models

arXiv:2606. 17417v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on a variety of audio understanding tasks but continue to struggle with temporal reasoning, a fundamental capability central to human auditory perception.

By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Sarah Wiegreffe, Dinesh Manocha, Ramani Duraiswami

llms fine-tuning benchmarks

Related stories