Researchers introduce DR Pixel, an open-source multimodal deep-research agent that retrieves and reasons over rendered page images rather than OCR text. It operates over 1.06 million pages and is evaluated on DRPixelBench, a new benchmark for page-native research.
Why it matters
It preserves tables, figures and equations lost in text extraction, potentially improving accuracy on scientific literature tasks.
Analysis
DR Pixel tests whether vision-language models can do end-to-end research without OCR. If page images retain layout and visual evidence better than extracted text, benchmarks and tools may favour multimodal retrieval. Main uncertainty: cost, latency and retrieval accuracy at scale, and whether gains hold beyond its benchmark.
Source: arXiv
AI disclosure: this article was produced with AI assistance and reviewed for accuracy.
