1
Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning
首个结合智能体主动感知与全模态交互的多跳视听推理框架,突破被动感知局限
arXiv:2605.28192v1 Announce Type: new Abstract: Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often spar…