Paper page - DR Pixel: Page-Native Deep Research with Vision-Language Models

Source: https://huggingface.co/papers/2611.03097

Abstract

DR Pixel is an open-source multimodal agent that performs deep research directly on rendered document page images, improving retrieval and reasoning over scientific papers through counterfactual credit reweighting.

Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whethervision-language models(VLMs) can enablepage-native deep research: directly retrieving and reasoning over rendered document page images. We introduceDR Pixel, the first open-source end-to-end multimodal DR agent that uses rendered page images as its sole retrieval and reasoning unit, operating over a corpus of 1.06M pages. To evaluate this setting, we constructDRPixelBench, a benchmark on scientific papers requiring reasoning over text, figures, tables, and equations. Surprisingly, page-native DR already works well without training, outperforming OCR-based baselines across state-of-the-art models like GPT-5.4, Gemini-3.5-Flash, and Qwen3.6-27B, while requiring fewer tool calls. We next turn to DR training. A key challenge is that teacher trajectories foragentic supervised finetuningare noisy, mixing critical reasoning and action steps with redundant or failed attempts. To address this, we introducecounterfactual credit reweighting, a fine-grained credit assignment method that weights individual reasoning and action steps by their counterfactual contribution to the final answer. Our training improvesretrieval recallby about 15 points and final accuracy by over 10 points onDRPixelBench, and likewise outperforms the untrained baseline on four existing benchmarks. On out-of-distribution ViDoRe-V3,DR Pixelcomes within 1.8 points of an oracle that is given the gold pages directly. Our results suggest that the conventional OCR-then-retrieve pipeline is not only unnecessary but suboptimal: directly retrieving and reasoning over visual document pages makes complex DR both more effective and more efficient.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2611\.03097

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2611.03097 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2611.03097 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2611.03097 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.