AI RESEARCH

Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search

arXiv CS.LG

ArXi:2605.08762v1 Announce Type: cross Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively search for cross-modal evidence remains underexplored. In this paper, we