AI RESEARCH
Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
arXiv CS.CL
•
ArXi:2604.18187v1 Announce Type: cross Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely either on supervised chain-of-thought (CoT) fine-tuning, which is limited by