Skip to content
Sagan

Paper

Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning

Unreadunread

AI summary

arXiv:2606. 15231v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated impressive capabilities in many visual tasks, but they often struggle with factual grounding when confronted with complex, open-world scenarios.