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

Researchers propose Visual-Seeker, a multimodal deep search agent that actively reasons over visual details to perform multi-hop, cross-modal search. The agent achieves state-of-the-art results on five benchmarks, surpassing proprietary models, by using a synthesized dataset of 5K trajectories for training.

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. While recent multimodal deep search agents attempt to address this issue by utilizing external tools, the visual-native search paradigm remains underexplored. Existing methods primarily rely on simple images with explicit semantics and text-only evidence trajectories, limiting the agent's ability to perform multi-hop, cross-modal reasoning and search. To address these limitations, we propose Visual-Seeker, a visual-native multimodal deep search agent via active visual reasoning. Rather than treating vision as a static input, our agent actively attends to fine-grained visual details, dynamically harvests visual evidence throughout the search process. To unlock its visual-native potential, we design an active visual reasoning data pipeline and synthesize 5K high-quality multimodal trajectories for model training. Extensive experiments demonstrate the state-of-the-art performance across five challenging multimodal search benchmarks, even surpassing several proprietary models, validating robust visual-native reasoning and search in real-world web environments. The code and data can be accessed at: https://github.com/ZhengboZhang/Visual-Seeker.