cs.AINov 7, 2026

MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs

Authors: Haoran Luo, Ziyue Zhu, Shangyang Wu, Linhao Luo, Yikai Guo, Qika Lin, Fangzhi Xu, Jiapu Wang, 

Organizations: Nanyang Technological University · Beijing University of Posts and Telecommunications · Monash University · Beijing Institute of Computer Technology and Application · 

Abstract

Driven by increasingly complex real-world applications, Retrieval-Augmented Generation (RAG) has evolved from textual pipelines to multimodal settings, comprising two complementary dimensions: knowledge organization and retrieval enhancement. However, existing methods still face challenges of high construction cost, context window limitations, and the lack of unified training across offline and online knowledge sources. To address these challenges, we propose MMGraph-Agent, a unified multimodal RAG framework based on cache-inspired multimodal knowledge hypergraphs. MMGraph-Agent enables extremely lightweight hypergraph construction with zero API cost and dynamic memory-based retrieval that alleviates long-context issues. Experiments across offline, online, and joint retrieval settings demonstrate consistent improvements in performance, efficiency, and architectural unification. Our software and data are publicly available at https://github.com/LHRLAB/MMGraph-Agent.

Figures & tables

Explore similar work

CardsList
  1. MG2^2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

    Apr 4, 2026Sijun Dai, Qiang Huang, Xiaoxing You +1Cross-Modal LearningMultimodal RAG

  2. MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

    Jun 24, 2026Xiaochen Wang, Bao Hoang, Han Liu +2Multimodal RAGRetrieval-Augmented Generation

  3. EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval

    Jul 14, 2026Jiashi Lin, Changhong Jiang, Xiangru Lin +12Multimodal RAGGraph Retrieval-Augmented Generation