DocDancer: Towards Agentic Document-Grounded Information Seeking
This addresses the need for better tool utilization in document-grounded information seeking, though it appears incremental as it builds on existing DocQA methods.
The authors tackled the problem of document question answering by introducing DocDancer, an open-source agent framework that models document exploration and comprehension, achieving effectiveness on benchmarks like MMLongBench-Doc and DocBench.
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.