Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs

2025-11-11

AI Summary

Existing GraphRAG research predominantly focuses on RDF knowledge graphs and SPARQL queries, overlooking the potential of Cypher and labeled property graph (LPG) databases for scalable reasoning. This paper introduces the first multi-agent framework for text-to-Cypher query generation tailored to LPGs, integrating a large language model–driven workflow, iterative query refinement, and content-aware feedback-based error correction. Evaluated on Memgraph using CypherBench and an industrial building information modeling (IFC) dataset, the framework achieves high accuracy in Cypher generation across both general-domain and digital twin scenarios. It significantly improves semantic consistency and syntactic correctness over baselines. Experimental results demonstrate the framework’s effectiveness, robustness, and scalability for industrial-grade structured knowledge retrieval from LPG databases.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Description Logics
• Natural Language Processing: Question Answering

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Agentic search

Abstract

While Retrieval-Augmented Generation (RAG) methods commonly draw information from unstructured documents, the emerging paradigm of GraphRAG aims to leverage structured data such as knowledge graphs. Most existing GraphRAG efforts focus on Resource Description Framework (RDF) knowledge graphs, relying on triple representations and SPARQL queries. However, the potential of Cypher and Labeled Property Graph (LPG) databases to serve as scalable and effective reasoning engines within GraphRAG pipelines remains underexplored in current research literature. To fill this gap, we propose Multi-Agent GraphRAG, a modular LLM agentic system for text-to-Cypher query generation serving as a natural language interface to LPG-based graph data. Our proof-of-concept system features an LLM-based workflow for automated Cypher queries generation and execution, using Memgraph as the graph database backend. Iterative content-aware correction and normalization, reinforced by an aggregated feedback loop, ensures both semantic and syntactic refinement of generated queries. We evaluate our system on the CypherBench graph dataset covering several general domains with diverse types of queries. In addition, we demonstrate performance of the proposed workflow on a property graph derived from the IFC (Industry Foundation Classes) data, representing a digital twin of a building. This highlights how such an approach can bridge AI with real-world applications at scale, enabling industrial digital automation use cases.

Problem

• Develops text-to-Cypher framework for querying labeled property graphs
• Addresses underexplored use of Cypher queries in GraphRAG systems
• Creates natural language interface for industrial digital automation

Innovation

• Multi-Agent GraphRAG system for text-to-Cypher generation
• Automated Cypher query generation using LLM-based workflow
• Iterative correction with feedback loop refines query semantics