SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio representations into a large language model (LLM) backbone to enable multimodal reasoning. Recent test-time reinforcement learning (TTRL) methods further improve LLM reasoning capability by leveraging unlabelled test data after pre-training. However, the importance of the perceptual capability of LALMs remains underexplored, particularly how much acoustic evidence is integrated and relied upon during reasoning, and how this contributes to final task p

Read original source ↗ Open in workspace

recordType

paper

region

Global