虽然多模态检索增强一代 (MM-RAG) 已显示出有希望的结果,，但它仍然难以应对复杂的多跳推理任务。现有方法主要关注独立的实例级匹配,，它通常无法捕获跨模式和文档的显式关系。尽管图增强方法引入了结构建模,，但它们在多模式场景中面临着根本性挑战:，结合细粒度视觉特征会导致快速图扩展和检索噪声,，而粗粒度表示会导致关键局部证据的丢弃。为了解决这个困境,，我们提出 DualG-MRAG, 一个双层框架，它引入了一种解耦架构，包括多模态 RAG 的宏观推理和微观匹配图。具体来说,通过将全局结构推理与细粒度证据匹配分离来抑制检索噪声,我们构建了用于全局拓扑路由的宏观图和用于精确局部验证的微观图。随后, 为了实现跨异构证据源的动态相关性传播,，我们通过 GNN 检索器将检索制定为查询驱动的消息传递过程。此外,为生成模型提供连贯的结构指导,我们引入了一种动态编程解码机制，该机制直接从GNN的前向传递,中提取显式推理路径，替换独立文档块的标准输入。大量实验表明，DualG-MRAG 在证据召回率和复杂 QA 准确性方面均优于基线。

While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, which often fails to capture explicit relationships across modalities and documents. Although Graph-enhanced methods introduce structural modeling, they face a fundamental challenge in multimodal scenarios: incorporating fine-grained visual features leads to rapid graph expansion and retrieval noise, whereas coarse-grained representations cause the discarding of critical local evidence. To address this dilemma, we propose DualG-MRAG, a Dual-tier framework that introduces a decoupled architecture comprising Macro-reasoning and Micro-matching Graphs for Multimodal RAG. Specifically, to suppress retrieval noise by isolating global structural reasoning from fine-grained evidence matching, we construct a Macro Graph for global topological routing and a Micro Graph for precise local verification. Subsequently, to enable dynamic relevance propagation across heterogeneous evidence sources, we formulate retrieval as a query-driven message passing process via a GNN Retriever. Furthermore, to provide the generative model with coherent structural guidance, we introduce a dynamic programming decoding mechanism that extracts explicit reasoning paths directly from the GNN的 forward pass, replacing the standard input of isolated document chunks. Extensive experiments demonstrate that DualG-MRAG outperforms baselines in both evidence recall and complex QA accuracy.

科目:人工智能(cs.AI)

Subjects: Artificial Intelligence (cs.AI)