arXivTiansheng Hu, Yichuan Wang, James V. Talwar, Nicholas Tomlin, Chen Zhao, Sewon MinMon, Nov 2, 2026, 5:13 AM PST
score 16.8
AI research agent reads document pages as images instead of OCR text
Original: DR Pixel: Page-Native Deep Research with Vision-Language Models
Source: arxiv.org ↗
Writing ELI5 summary…