# SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

## TL;DR

SQL-of-Thought introduces a multi-agent framework for text-to-SQL conversion that leverages in-context learning and guided error correction to achieve state-of-the-art performance on complex benchmarks.

## Contribution

It presents a novel multi-agent approach with taxonomy-guided dynamic error correction, improving robustness and accuracy over prior static correction methods.

## Key findings

- Achieves state-of-the-art results on the Spider dataset
- Demonstrates effectiveness of taxonomy-guided dynamic error correction
- Enhances robustness of text-to-SQL systems through multi-agent reasoning

## Abstract

Converting natural language queries into SQL queries is a crucial challenge in both industry and academia, aiming to increase access to databases and large-scale applications. This work examines how in-context learning and chain-of-thought can be utilized to develop a robust solution for text-to-SQL systems. We propose SQL-of-Thought: a multi-agent framework that decomposes the Text2SQL task into schema linking, subproblem identification, query plan generation, SQL generation, and a guided correction loop. Unlike prior systems that rely only on execution-based static correction, we introduce taxonomy-guided dynamic error modification informed by in-context learning. SQL-of-Thought achieves state-of-the-art results on the Spider dataset and its variants, combining guided error taxonomy with reasoning-based query planning.