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

arXiv: https://arxiv.org/abs/2608.26117 · HTML: https://mlsanity.com/paper/2608.26117/

## 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 17 Jun 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)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology](https://mlsanity.com/paper/2406.11912/) (2024)
- [A Decade of Knowledge Graphs in Natural Language Processing: A Survey](https://mlsanity.com/paper/2210.00105/) (2022)
- [Demystifying Graph Databases: Analysis and Taxonomy of Data Organization, System Designs, and Graph Queries](https://mlsanity.com/paper/1910.09017/) (2019)
- [PG-Schema: Schemas for Property Graphs](https://mlsanity.com/paper/2211.10962/) (2022)
- [The World of Graph Databases from An Industry Perspective](https://mlsanity.com/paper/2211.13170/) (2022)
- [Rel2Graph: Automated Mapping From Relational Databases to a Unified Property Knowledge Graph](https://mlsanity.com/paper/2310.01080/) (2023)
- [Schema Validation and Evolution for Graph Databases](https://mlsanity.com/paper/1902.06427/) (2019)
- [Cortex: Harnessing Correlations to Boost Query Performance](https://mlsanity.com/paper/2012.06683/) (2020)
- [Towards a Complete Direct Mapping From Relational Databases To Property Graphs](https://mlsanity.com/paper/2210.00457/) (2022)
- [Importing Relationships into a Running Graph Database Using Parallel Processing](https://mlsanity.com/paper/2005.04093/) (2020)
- [A Unified Metamodel for NoSQL and Relational Databases](https://mlsanity.com/paper/2105.06494/) (2021)
- [Performance Comparison Analysis of ArangoDB, MySQL, and Neo4j: An Experimental Study of Querying Connected Data](https://mlsanity.com/paper/2401.17482/) (2024)

## Abstract (arXiv)

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.