DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation

  • 类型：arxiv
  • 标识：2607.28580
  • 链接：http://arxiv.org/abs/2607.28580v1
  • 主分类：rag
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：DualG-MRAG is proposed, a Dual-tier framework that introduces a decoupled architecture comprising Macro-reasoning and Micro-matching Graphs for Multimodal RAG to suppress retrieval noise by isolating global structural reasoning from fine-grained evidence matching, and introduces a dynamic programming decoding mechanism that extracts explicit reasoning paths directly from the GNN's forward pass.
  • OpenAlex ID：W7171972818
  • OpenAlex DOI：10.48550/arxiv.2607.28580
  • DOI：10.48550/arxiv.2607.28580
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.28580
  • OpenAlex更新：2026-08-26
  • 副分类：multimodal
  • 待LLM分类：否
  • 标题中文：DualG-MRAG：面向多模态 RAG 的宏观推理与微观匹配解耦
  • TLDR中文：提出 DualG-MRAG，一种面向多模态 RAG 的双层框架，解耦 Macro-reasoning 与 Micro-matching Graph 两类图结构，通过分离全局结构推理与细粒度证据匹配来抑制检索噪声，并引入动态规划解码机制，从 GNN 前向过程中直接提取显式推理路径。
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-31-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-01-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-02-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-03-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]