{"type":"post","id":"dr-pixel-open-source-deep-research-agent-that-74e244","slug":"dr-pixel-open-source-deep-research-agent-that-74e244","title":"DR Pixel: open-source deep research agent that retrieves and reasons over rendered page images instead of OCR text","description":"DR Pixel is an open-source deep-research agent that retrieves rendered document pages and reasons over page images rather than converting papers into OCR text first.","retrieval_nugget":"DR Pixel is an open-source deep-research agent that retrieves rendered document pages and reasons over page images rather than converting papers into OCR text first. Its authors report stronger benchmark performance than OCR-based baselines with fewer tool calls, offering teams a testable alternative for research workflows over visually dense PDFs.","published_at":"2026-11-04","updated_at":"2026-11-04","record_date":"2026-11-04","date_kind":"published_at","topics":["agents","retrieval","multimodal"],"entities":["DR Pixel","DRPixelBench","GPT-5.4","Gemini-3.5-Flash","Qwen3.6-27B","ViDoRe-V3","arXiv"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"DR Pixel adds an open-source research agent that retrieves and reasons directly over rendered page images, with a 1.06M-page corpus and benchmark gains; prior coverage addressed image-based PDF search and OCR retrieval.","prior_refs":[],"source_url":"https://arxiv.org/abs/2611.03097","source_urls":["https://arxiv.org/abs/2611.03097"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:dr-pixel-open-source-deep-research-agent-that-74e244","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/dr-pixel-open-source-deep-research-agent-that-74e244/","markdown":"https://newruntime.com/posts/dr-pixel-open-source-deep-research-agent-that-74e244.md","json":"https://newruntime.com/posts/dr-pixel-open-source-deep-research-agent-that-74e244.json"},"related_shifts":["document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm"],"markdown_url":"https://newruntime.com/posts/dr-pixel-open-source-deep-research-agent-that-74e244.md","next_reads":[{"type":"topic","path":"/topics/agents/","url":"https://newruntime.com/topics/agents/","title":"Agents","reason":"Explore the agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agents.md","json_url":"https://newruntime.com/topics/agents.json"},{"type":"topic","path":"/topics/retrieval/","url":"https://newruntime.com/topics/retrieval/","title":"Retrieval","reason":"Explore the retrieval topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/retrieval.md","json_url":"https://newruntime.com/topics/retrieval.json"},{"type":"topic","path":"/topics/multimodal/","url":"https://newruntime.com/topics/multimodal/","title":"Multimodal","reason":"Explore the multimodal topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/multimodal.md","json_url":"https://newruntime.com/topics/multimodal.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}