Hybrid Multi-Agent GraphRAG for E-Government: Towards a Trustworthy AI Assistant
Top Cited Papers
Open Access
- 4 June 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 6315
Abstract
As public institutions increasingly adopt AI-driven virtual assistants to support transparency and citizen engagement, the need for explainable, accurate, and context-aware language systems becomes vital. While traditional retrieval-augmented generation (RAG) frameworks effectively integrate external knowledge into Large Language Models (LLMs), their reliance on flat, unstructured document retrieval limits multi-hop reasoning and interpretability, especially with complex, structured e-government datasets. This study introduces a modular, extensible, multi-agent graph retrieval-augmented generation (GraphRAG) framework designed to enhance policy-focused question answering. This research aims to provide an overview of hybrid multi-agent GraphRAG architecture designed for operational deployment in e-government settings to support explainable AI systems. The study focuses on how the hybrid integration of standard RAG, embedding-based retrieval, real-time web search, and LLM-generated structured Graphs can optimize knowledge discovery from public e-government data, thereby reinforcing factual grounding, reducing hallucinations, and enhancing the quality of complex responses. To validate the proposed approach, we implement and evaluate the framework using the European Commission’s Press Corner as a data source, constructing graph-based knowledge representations and embeddings, and incorporating web search. This work establishes a reproducible blueprint for deploying AI systems in e-government that require structured reasoning in comprehensive and factually accurate question answering.Keywords
This publication has 19 references indexed in Scilit:
- Enhancing Policy Generation with GraphRAG and YouTube Data: A Logistics Case StudyElectronics, 2025
- A Multimodal Framework Embedding Retrieval-Augmented Generation with MLLMs for Eurobarometer DataAI, 2025
- Swamped with Too Many Articles? GraphRAG Makes Getting Started EasyAI, 2025
- Adaptive Control of Retrieval-Augmented Generation for Large Language Models Through Reflective TagsElectronics, 2024
- TravelRAG: A Tourist Attraction Retrieval Framework Based on Multi-Layer Knowledge GraphISPRS International Journal of Geo-Information, 2024
- A survey on multimodal large language modelsNational Science Review, 2024
- StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented GenerationProceedings of the AAAI Symposium Series, 2024
- Graph Retrieval-Augmented Generation for Large Language Models: A Survey2024
- Enhancing E-Government Services through State-of-the-Art, Modular, and Reproducible Architecture over Large Language ModelsApplied Sciences, 2024
- Artificial Intelligence and the Public Sector—Applications and ChallengesInternational Journal of Public Administration, 2018