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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

• llms
• reinforcement-learning
• fine-tuning