AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

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

Haoran Luo, Ziyue Zhu, Shangyang Wu, Linhao Luo, Yikai Guo, Qika Lin, Fangzhi Xu, Jiapu Wang, Xiaobao Wu, Yifan Zhu, Anh Tuan Luu

NeurIPS 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MMGraph-Agent, an agentic multimodal RAG system that organizes knowledge as cache-inspired multimodal knowledge hypergraphs to address construction cost, context limits, and unified offline/online knowledge training.

Problem

Multimodal RAG suffers from high knowledge-graph construction cost, limited context windows, and lack of unified training across offline and online knowledge sources.

Approach

Combines a cache-inspired multimodal knowledge hypergraph for knowledge organization with an agentic retrieval process, aiming to unify offline and online knowledge sourcing under one training scheme. Details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MMGraph-Agent-3B over second-best baseline per datasetQwen2.5-VL-3B agent · 23 multimodal QA datasetstoken F1: +11.6 F1 on averageImproved
MMGraph-Agent vs MMSearch-R1 on OOD datasetsQwen2.5-VL-3B agent · 8 held-out OOD datasetstoken F1: +13.0 F1Improved
add multimodal hypergraph (ablation)MMGraph-Agent · K+Webtoken F1: +16.6Improved
add cache-inspired memory (ablation)MMGraph-Agent · K+Webtoken F1: +6.4Improved
add offline-trained GRPO policy (ablation)MMGraph-Agent · K+Webtoken F1: +6.3Improved
add retrieval (ablation)MMGraph-Agent · K+Webtoken F1: +3.6Improved
use multimodal hypergraph instead of pairwise-edge KG (ablation)MMGraph-Agent · 23 datasetstoken F1: wins on 23/23 datasetsImproved
add L1 cache with C=5 per-bank budget (ablation)MMGraph-Agent · long-chain episodestokens and F1: 67% fewer tokens, +3.4 F1Improved
replace LLM extraction with spaCy NER and frozen CLIP for graph constructionMMGraph-Agent · construction costF1 and API cost: overall F1 30.0 at zero API costImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy