| title | From Web to Pixels: Bringing Agentic Search into Visual Perception |
|---|---|
| authors | Bokang Yang, Xinyi Sun, Kaituo Feng, Xingping Dong, Dongming Wu, Xiangyu Yue |
| date | 2026-05-12 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.12497 |
| upvotes | 12 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for identifying a target is already in the image or frozen model knowledge. We study a more practical yet harder open-world case where a visible object must first be resolved from external facts, recent events, long-tail entities, or multi-hop relations before it can be localized. We formalize this challenge as Perception Deep Research and introduce WebEye, an object-anchored benchmark with verifiable evidence, knowledge-intensive queries, precise box/mask annotations, and three task views: Search-based Grounding, Search-based Segmentation, and Search-based VQA. WebEyes contains 120 images, 473 annotated object instances, 645 unique QA pairs, and 1,927 task samples. We further propose Pixel-Searcher, an agentic search-to-pixel workflow that resolves hidden target identities and binds them to boxes, masks, or grounded answers. Experiments show that Pixel-Searcher achieves the strongest open-source performance across all three task views, while failures mainly arise from evidence acquisition, identity resolution, and visual instance binding. |
cite
@misc{yang2026from,
title={From Web to Pixels: Bringing Agentic Search into Visual Perception},
author={Bokang Yang and Xinyi Sun and Kaituo Feng and Xingping Dong and Dongming Wu and Xiangyu Yue},
year={2026},
eprint={2605.12497},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.12497}
}