发表机构
School of Electrical and Information Engineering, Tianjin University; The International Joint Institute of Tianjin University; Department of Automation, Tsinghua University（天津大学电气与信息工程学院; 天津大学国际联合学院; 清华大学自动化系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究长文档多模态问答，提出TAP-RAG框架，含任务感知策略控制器及两个执行器，能预测任务先验、估计证据信号并生成策略，在多模态文档图上扩展证据，在相关数据集上取得最佳总体准确率。
AI 中文摘要
长文档多模态问答不仅仅是从大文档中检索相关片段。不同查询需要不同的证据行为。现有多模态RAG系统通过文本块、页面图像、图形链接或异构文档元素改善证据获取，但采用查询无关的证据使用策略。我们提出TAP-RAG，一种用于长文档多模态问答的任务感知策略控制RAG框架。它包含主控制器、任务感知策略控制器（TAPC）以及两个策略引导的证据执行器。TAPC预测任务先验，估计视觉/局部/全局证据信号并生成可执行策略。TA-QFD在多模态文档图上扩展文本和结构证据，TAVE在需要视觉或布局证据时选择性检查页面图像。一个 guarded合成阶段融合文本、视觉和结构证据，支持不足时弃权。在DocBench和MMLongBench-Doc上，TAP-RAG在比较系统中取得最佳总体准确率。
英文摘要
Long-document multimodal question answering requires more than retrieving relevant chunks from a large document. Different queries require different evidence behavior. Existing multimodal RAG systems improve evidence access through text chunks, page images, graph links, or heterogeneous document elements, but they often apply a largely query-agnostic evidence-use strategy. We present TAP-RAG, a task-aware policy-controlled RAG framework for long-document multimodal QA. TAP-RAG contains a main controller, the Task-Aware Policy Controller (TAPC), and two policy-guided evidence executors: Task-Aware Query-Guided Flow Diffusion (TA-QFD) and Task-Aware Visual Enhancement (TAVE). For each query, TAPC predicts the task prior, estimates visual/local/global evidence signals, and produces an executable policy. TA-QFD then expands textual and structural evidence over the multimodal document graph, while TAVE selectively inspects page images when visual or layout evidence is needed. A guarded synthesis stage fuses text, visual, and structural evidence and abstains when support is insufficient. On DocBench and MMLongBench-Doc, TAP-RAG achieves the best overall accuracy among the compared systems, improving over a matched multimodal-RAG baseline by +9.1 points (61.1 to 70.2) and +4.5 points (42.2 to 46.7), respectively.
Comments18 pages, 6 figures, 9 tables
