[2606.00610] MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

-->

Computer Science > Information Retrieval

arXiv:2606.00610 (cs)

[Submitted on 30 May 2026]

Title:MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

Authors:Chuanjie Wu, Zhishang Xiang, Yunbo Tang, Zerui Chen, Qinggang Zhang, Jinsong Su<br>View a PDF of the paper titled MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation, by Chuanjie Wu and 5 other authors

View PDF<br>HTML (experimental)

Abstract:Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge. Although effective for simple queries, traditional RAG struggles with large-scale, unstructured corpora where information is highly fragmented. Graph-based RAG (GraphRAG) incorporates knowledge graphs to capture structural relationships, enabling more comprehensive retrieval for complex reasoning. However, existing GraphRAG methods rely on isolated, fragment-level extraction for graph construction, lacking a global perspective on the whole corpus. As a result, these methods frequently lead to thematically inconsistent, logically conflicting, and structurally fragmented graphs that degrade retrieval performance. In this paper, we propose MemGraphRAG, a novel framework that introduces a memory-based multi-agent system to ensure high-quality graph construction. Specifically, MemGraphRAG employs a collaborative society of agents supported by shared memory, which provides a unified global context throughout the extraction process. This mechanism allows agents to dynamically resolve logical conflicts and maintain structural connectivity throughout the corpus. Furthermore, we propose a memory-aware hierarchical retrieval algorithm tailored for the constructed graph. Extensive experiments on multiple benchmarks demonstrate that MemGraphRAG outperforms the state-of-the-art baseline models with comparable efficiency. Our code is available at this https URL.

Comments:<br>Accepted by KDD 2026

Subjects:

Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)

Cite as:<br>arXiv:2606.00610 [cs.IR]

(or<br>arXiv:2606.00610v1 [cs.IR] for this version)

https://doi.org/10.48550/arXiv.2606.00610

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Qinggang Zhang [view email]<br>[v1]<br>Sat, 30 May 2026 08:18:53 UTC (3,740 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation, by Chuanjie Wu and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.IR

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.AI<br>cs.MA

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)