Metraipolis › archive › dc_ff08e35f4718

From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvement — arXiv:2608.26117

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26117
License (as archived)
CC0-1.0
Archived
2026-10-17T14:23:57.388Z
SHA-256 of the archived text
ed6058694e48b8faec0edf1650fa0599f1524f528e1436fadf01f1aa45364d5d
Stable URL of this page
https://metraipolis.com/documento/dc_ff08e35f4718

How to cite

From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvement — arXiv:2608.26117 — arXiv (en), https://arxiv.org/abs/2608.26117 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff08e35f4718 (Metraipolis archive dc_ff08e35f4718, sha256 ed6058694e48b8faec0edf1650fa0599f1524f528e1436fadf01f1aa45364d5d)
BibTeX
@misc{dcff08e35f4718,
  title = {From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvement — arXiv:2608.26117},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26117},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff08e35f4718; sha256 ed6058694e48b8faec0edf1650fa0599f1524f528e1436fadf01f1aa45364d5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26117. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

RDBMS (Relational Database Management System) databases face several limitations, including slow execution with multi-hop queries and a lack of explainability by graphical interpretations. In contrast, Graph database offers a more intuitive and efficient data schema that performs faster execution on large datasets. Most existing RDBMS conversion pipelines focus on running traditional loading commands and relying on Cypher queries. However, the efficiency of using an LLM to generate an effective graph data schema, significantly reducing the ambiguity of the graph database, remains underexplored in the current research literature. This paper presents a novel algorithm that bridges RDBMS and graph database by using a novel LLM-powered ETL agent to standardize table and column names before saving them to the Data Mart. A Multi-Agent System generates a looping discussion between ETL, Analyzer, and Graph agents to optimize the final design through an iterative process of suggesting and scoring the graph database schema. We ensure that the final graph database meets three criteria before being accepted for data conversion: Accuracy, Groundedness, and Faithfulness. This system demonstrates an effective pipeline to automatically convert a tabular database into a graph database through a comprehensive end-to-end process. Our study highlights notable efficiency in using the converted graph database, which is measured on 1,081 samples of the BFSI dataset across three levels of complexity (easy, medium, and hard). Specifically, CypherAgent achieves an 85.6% accuracy for Q&A tasks using a Graph database, which is 12.12% higher than the accuracy achieved by an SQLAgent on the RDBMS database type PostgreSQL, for all queries. Additionally, the Graph database demonstrates faster performance, reducing latency by approximately 3 times.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26117 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.582Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).