VistaHop: Benchmarking Multi-hop Visual Reasoning for Visual DeepSearch 事件

VistaHop: Benchmarking Multi-hop Visual Reasoning for Visual DeepSearch arXiv:2606.03273v1 Announce Type: new Abstract: Visual DeepSearch requires multimodal large reasoning model (MLRM) agents to answer complex visual queries by repeatedly inspecting image regions, grounding intermediate reasoning in visual evidence, and connecting fine-grained clues across long reasoning chains. However, existing benchmarks mainly focus on single-step visual understanding or static image-question answering, o