STaRQ-Agent-Investigating Generalization in Knowledge Graph Question Answering via a Multi-Agent Collaborative Framework
Open Access
- 6 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 59158-59170
Abstract
Generalization to different Knowledge Graphs (KGs) is a core challenge of Knowledge Graph Question Answering (KGQA). Current models struggle to adapt to unseen KGs due to their underlying heterogeneity. Most approaches depend on data-hungry methods, such as supervised fine-tuning and KG-specific few-shot demonstrations. These systems are limited in cross-KG generalization, and may exhibit hallucination problems, especially in low-resource or domain-specific scenarios. This paper presents STaRQ-Agent, an LLM-based multi-agent collaborative framework for the KGQA generalization problem. It comprises a core agent for SPARQL query generation, accompanied by three supportive agents for schema selection, template generation, and query refinement. This collaborative framework helps mitigate hallucination problems inherent in LLMs. STaRQ-Agent was evaluated on LC-QuAD 1.0, QALD-9, MetaQA, and MatKGQA datasets in few-shot and zero-shot settings. Experimental results demonstrate strong overall generalization across diverse KGs, without requiring high-quality annotated data, re-training, or fine-tuning. Specially, on LC-QuAD 1.0, QALD-9, and MetaQA, few-shot STaRQ-Agent outperforms the strongest baseline by 5.1%, 4.3%, and 0.7%, while zero-shot STaRQ-Agent shows only modest F1 drops of 8.7%, 12.3%, and 10.8%. Moreover, the state-of-the-art results on MatKGQA show its robust out-of-distribution generalization to novel KGs in low-resource specific domains.Keywords
Funding Information
- the Ministry of Research and Education (FKZ 13N16836)
This publication has 50 references indexed in Scilit:
- Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering2025
- Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answeringGigaScience, 2025
- Schema Item Matters in Knowledge Base Question Answering2023
- Knowledge Graphs in Education and Employability: A Survey on Applications and TechniquesIEEE Access, 2022
- SGPT: A Generative Approach for SPARQL Query Generation From Natural Language QuestionsIEEE Access, 2022
- EDG-Based Question Decomposition for Complex Question Answering over Knowledge Bases2021
- Knowledge Graphs in Manufacturing and Production: A Systematic Literature ReviewIEEE Access, 2021
- Research on Medical Question Answering System Based on Knowledge GraphIEEE Access, 2021
- Answering Natural Language Questions by Subgraph Matching over Knowledge GraphsIEEE Transactions on Knowledge and Data Engineering, 2017
- LC-QuAD: A Corpus for Complex Question Answering over Knowledge Graphs2017