# NAT-NL2GQL: A Novel Multi-Agent Framework for Translating Natural Language to Graph Query Language

arXiv: https://arxiv.org/abs/2412.10434 · HTML: https://mlsanity.com/paper/2412.10434/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## 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, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [On the Effectiveness of Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2211.15583/) (2022)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions](https://mlsanity.com/paper/2105.11644/) (2021)
- [The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models](https://mlsanity.com/paper/2408.07702/) (2024)
- [Graph Data Augmentation for Graph Machine Learning: A Survey](https://mlsanity.com/paper/2202.08871/) (2022)
- [Empirical Study of Zero-Shot NER with ChatGPT](https://mlsanity.com/paper/2310.10035/) (2023)
- [Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift](https://mlsanity.com/paper/2211.02843/) (2022)
- [E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL](https://mlsanity.com/paper/2409.16751/) (2024)
- [PURPLE: Making a Large Language Model a Better SQL Writer](https://mlsanity.com/paper/2403.20014/) (2024)
- [GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization](https://mlsanity.com/paper/2311.03157/) (2023)
- [D-Bot: Database Diagnosis System using Large Language Models](https://mlsanity.com/paper/2312.01454/) (2023)
- [Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL](https://mlsanity.com/paper/2402.16567/) (2024)
- [R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL](https://mlsanity.com/paper/2311.01862/) (2023)

## Built on by (most cited first, 9 of 9)

- [1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning](https://mlsanity.com/paper/2508.07667/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [Enhancing Text2Cypher with Schema Filtering](https://mlsanity.com/paper/2505.05118/) (2025)
- [Text2GraphQuery-Bench: A Text to Graph Query Benchmark](https://mlsanity.com/paper/2602.11745/) (2026)
- [Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation](https://mlsanity.com/paper/2606.14325/) (2026)
- [Multi-turn Natural Language to Graph Query Language Translation](https://mlsanity.com/paper/2508.01871/) (2025)
- [Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions](https://mlsanity.com/paper/2603.23375/) (2026)
- [Performance Evaluation of LLMs in Automated RDF Knowledge Graph Generation](https://mlsanity.com/paper/2603.29878/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

The emergence of Large Language Models (LLMs) has revolutionized many fields, not only traditional natural language processing (NLP) tasks. Recently, research on applying LLMs to the database field has been booming, and as a typical non-relational database, the use of LLMs in graph database research has naturally gained significant attention. Recent efforts have increasingly focused on leveraging LLMs to translate natural language into graph query language (NL2GQL). Although some progress has been made, these methods have clear limitations, such as their reliance on streamlined processes that often overlook the potential of LLMs to autonomously plan and collaborate with other LLMs in tackling complex NL2GQL challenges. To address this gap, we propose NAT-NL2GQL, a novel multi-agent framework for translating natural language to graph query language. Specifically, our framework consists of three synergistic agents: the Preprocessor agent, the Generator agent, and the Refiner agent. The Preprocessor agent manages data processing as context, including tasks such as name entity recognition, query rewriting, path linking, and the extraction of query-related schemas. The Generator agent is a fine-tuned LLM trained on NL-GQL data, responsible for generating corresponding GQL statements based on queries and their related schemas. The Refiner agent is tasked with refining the GQL or context using error information obtained from the GQL execution results. Given the scarcity of high-quality open-source NL2GQL datasets based on nGQL syntax, we developed StockGQL, a dataset constructed from a financial market graph database. It is available at: https://github.com/leonyuancode/StockGQL. Experimental results on the StockGQL and SpCQL datasets reveal that our method significantly outperforms baseline approaches, highlighting its potential for advancing NL2GQL research.