Comprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). Existing approaches falter on a fundamental challenge: evidence localization. They struggle to retrieve relevant pages and overlook fine-grained details within visual elements, leading to limited performance and model hallucination. To address this, we propose DocLens, a tool-augmented multi-agent framework that effectively ``zooms in'' on evidence like a lens. It first navigates from the full document to specific visual elements on relevant pages, then employs a sampling-adjudication mechanism to generate a single, reliable answer. Paired with Gemini-2.5-Pro, DocLens achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts. The framework's superiority is particularly evident on vision-centric and unanswerable queries, demonstrating the power of its enhanced localization capabilities.
@article{arxiv.2511.11552,
title = {DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding},
author = {Dawei Zhu and Rui Meng and Jiefeng Chen and Sujian Li and Tomas Pfister and Jinsung Yoon},
journal= {arXiv preprint arXiv:2511.11552},
year = {2025}
}