MAGE-RAG：面向长文档问答的多粒度自适应图证据多模态RAG
MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA
AI总结：
提出MAGE-RAG框架，通过离线构建包含页面和元素节点的证据图，在线自适应构建证据子图，平衡证据覆盖与噪声控制，在长文档多模态问答中取得最优性能。
摘要：
长文档多模态问答要求系统在长PDF中定位稀疏证据，并整合来自文本、表格、图像、图表和复杂布局的线索。现有RAG方法大多依赖于文本块或页面的固定Top-k检索。文本检索可以压缩上下文，但往往丢失视觉和布局信息；页面级视觉检索保留原始页面，但也会将大量无关区域送入阅读器，导致证据覆盖、噪声和推理成本之间的静态权衡。本文提出MAGE-RAG，一种用于长文档多模态问答的多粒度自适应图证据框架。MAGE-RAG以页面检索作为查询时证据构建的入口。离线阶段，它构建一个包含页面节点和元素节点的证据图，编码包含关系、阅读顺序、布局邻接、章节层次和语义邻居关系。查询时，在线证据控制器在显式预算下迭代地激活、打开、搜索和剪枝证据。生成的证据子图随后被渲染为结构化的多模态阅读器输入，使LVLM能够在有限上下文中消费紧凑且相关的证据。在LongDocURL和MMLongBench-Doc上，我们建立了统一的比较和分析协议，涵盖直接MLLM、文本RAG、页面级视觉RAG和图/智能体RAG。实验表明，MAGE-RAG在LongDocURL上达到52.75的整体准确率，在MMLongBench-Doc上达到53.26的准确率和51.19的F1。细粒度分解、预算-性能曲线、消融和基于轨迹的分析进一步表明，查询时证据子图构建能够平衡分散证据覆盖与上下文噪声控制。我们的代码可在https://github.com/laonuo2004/MAGE-RAG.git获取。
英文摘要：
Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Existing RAG methods mostly rely on fixed Top-k retrieval over text chunks or pages. Text retrieval can compress the context but often loses visual and layout information; page-level visual retrieval preserves the original page, yet it also sends large irrelevant regions to the reader, leading to a static trade-off among evidence coverage, noise, and inference cost. This paper proposes MAGE-RAG, a multigranular adaptive graph evidence framework for long-document multimodal QA. MAGE-RAG uses page retrieval as the entry point for query-time evidence construction. Offline, it builds an evidence graph with page nodes and element nodes, encoding containment, reading order, layout adjacency, section hierarchy, and semantic-neighbor relations. At query time, an online evidence controller iteratively activates, opens, searches, and prunes evidence under explicit budgets. The resulting evidence subgraph is then rendered into structured multimodal reader input, allowing the LVLM to consume compact and relevant evidence within a limited context. On LongDocURL and MMLongBench-Doc, we establish a unified comparison and analysis protocol covering Direct MLLM, Text RAG, Page-level Visual RAG, and Graph/Agentic RAG. Experiments show that MAGE-RAG achieves 52.75 overall accuracy on LongDocURL, and 53.26 accuracy with 51.19 F1 on MMLongBench-Doc. Fine-grained breakdowns, budget-performance curves, ablations, and trace-based analysis further show that query-time evidence subgraph construction can balance dispersed evidence coverage with context-noise control. Our code is available at https://github.com/laonuo2004/MAGE-RAG.git.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
