# KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation

arXiv: https://arxiv.org/abs/2609.01780 · HTML: https://mlsanity.com/paper/2609.01780/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [Domain-specific Knowledge Graphs: A survey](https://mlsanity.com/paper/2011.00235/) (2020)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach](https://mlsanity.com/paper/2010.01195/) (2020)
- [SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions](https://mlsanity.com/paper/2407.11417/) (2024)
- [Large Language Model Enhanced Text-to-SQL Generation: A Survey](https://mlsanity.com/paper/2410.06011/) (2024)
- [Devstral: Fine-tuning Language Models for Coding Agent Applications](https://mlsanity.com/paper/2509.25193/) (2025)
- [Neural Machine Translating from Natural Language to SPARQL](https://mlsanity.com/paper/1906.09302/) (2019)
- [LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs](https://mlsanity.com/paper/2410.06062/) (2024)
- [SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graph](https://mlsanity.com/paper/2402.04627/) (2024)
- [Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunities](https://mlsanity.com/paper/2304.01311/) (2023)
- [A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts](https://mlsanity.com/paper/2502.16767/) (2025)
- [SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection](https://mlsanity.com/paper/2507.13859/) (2025)
- [A Decade of Scholarly Research on Open Knowledge Graphs](https://mlsanity.com/paper/2306.13186/) (2023)
- [FRASE: Structured Representations for Generalizable SPARQL Query Generation](https://mlsanity.com/paper/2503.22144/) (2025)
- [InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanations](https://mlsanity.com/paper/2511.02002/) (2025)
- [A Knowledge Graph Informing Soil Carbon Modeling](https://mlsanity.com/paper/2508.10965/) (2025)

## 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.