KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
Knowledge Graph Question Answering (KGQA) over RDF graphs remains challenging in domain-specific settings, where formal ontologies and curated text-SPARQL pairs are often unavailable. We present KGVoyager, a KG-agnostic agentic architecture that generates SPARQL queries from natural language questions by dynamically discovering graph structure and semantics, requiring only a query endpoint of the underlying graph. Using a think-act-observe loop with search, exploration, and execution tools, KGVoyager maps terms to graph IRIs, uncovers structure, and refines queries through execution feedback - all without pre-existing ontologies or examples. Unlike the prior state of the art, KGVoyager requires only a lightweight class index which renders it applicable for far more real-world endpoints. Across four benchmarks, KGVoyager improves F1 by ~8 points while cutting cost and runtime by ~22% each.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 40 references that are in the map. First posted on arXiv 1 Sep 2026.
Builds on
19 of 40 references.
References · 19
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2020Knowledge Graphscited by 619
- 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
- 2020Domain-specific Knowledge Graphs: A surveycited by 68
- 2022Modern Baselines for SPARQL Semantic Parsingcited by 34
- 2020Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approachcited by 31
- 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questionscited by 27
- 2024Large Language Model Enhanced Text-to-SQL Generation: A Surveycited by 24
- 2019Neural Machine Translating from Natural Language to SPARQLcited by 23
- 2025Devstral: Fine-tuning Language Models for Coding Agent Applicationscited by 23
- 2024LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphscited by 22
- 2024SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graphcited by 19
7 more
- 2023Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunitiescited by 9
- 2025A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Textscited by 8
- 2025SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injectioncited by 5
- 2023A Decade of Scholarly Research on Open Knowledge Graphscited by 2
- 2025FRASE: Structured Representations for Generalizable SPARQL Query Generationcited by 2
- 2025InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanationscited by 2
- 2025A Knowledge Graph Informing Soil Carbon Modelingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Towards Researcher Agents for Knowledge-Graph Question Answering
- 2025From Graph Retrieval to Schema Realization: Counterfactual Validation for Text-to-SPARQL over Heterogeneous Knowledge Graphs
- 2025RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
- 2025ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning
- 2026MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
- 2026Graph Query Generation with Constraint-guided Large Language Agents
- 2026Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmark
- 2026RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering