AgentNLQ: A General-Purpose Agent for Natural Language to SQL

TL;DR

This paper introduces AgentNLQ, a multi-agent system leveraging large language models to improve natural language to SQL conversion, achieving high accuracy on the BIRD benchmark.

Contribution

The study presents a novel multi-agent orchestrator, schema enrichment techniques, and demonstrates improved accuracy and generalizability in NL2SQL tasks.

Findings

Achieved 78.1% semantic accuracy on BIRD benchmark.

Developed a multi-agent orchestrator with self-correcting capabilities.

Enhanced schema representation improves SQL generation accuracy.

Abstract

Natural language to SQL (NL2SQL) conversion is an important problem for researchers and enterprises due to the ubiquitous importance of relational databases in broad-ranging practical problems. Despite the rapid advancements in the capabilities of LLMs, NL2SQL has not reached parity in accuracy with human expert SQL writers, hence needing additional improvements in NL2SQL algorithms. This study presents a new multi-agent method for NL2SQL that achieves 78.1% semantic accuracy on the BIg Bench for LaRge-scale Database (BIRD) benchmark. Our method leverages a semantically enriched representation of user-provided schema, adds user-provided business rules, and produces accurate SQL queries. The main contributions of this study are (a) We designed an optimized new orchestrator in a multi-agent solution that uses LLMs to plan, orchestrate, reflect, and self-correct to generate accurate SQL queries, (b) We developed an advanced schema enrichment method that creates context-aware metadata to improve accuracy, and (c) We demonstrated the accuracy and generalizability of the method across different domains and datasets by evaluating it on the BIRD-SQL benchmark.