Document Question Answering (DocQA) focuses on answering questions grounded in given documents, yet existing DocQA agents lack effective tool utilization and largely rely on closed-source models. In this work, we introduce DocDancer, an end-to-end trained open-source Doc agent. We formulate DocQA as an information-seeking problem and propose a tool-driven agent framework that explicitly models document exploration and comprehension. To enable end-to-end training of such agents, we introduce an Exploration-then-Synthesis data synthesis pipeline that addresses the scarcity of high-quality training data for DocQA. Training on the synthesized data, the trained models on two long-context document understanding benchmarks, MMLongBench-Doc and DocBench, show their effectiveness. Further analysis provides valuable insights for the agentic tool design and synthetic data.
@article{arxiv.2601.05163,
title = {DocDancer: Towards Agentic Document-Grounded Information Seeking},
author = {Qintong Zhang and Xinjie Lv and Jialong Wu and Baixuan Li and Zhengwei Tao and Guochen Yan and Huanyao Zhang and Bin Wang and Jiahao Xu and Haitao Mi and Wentao Zhang},
journal= {arXiv preprint arXiv:2601.05163},
year = {2026}
}