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

2025/08/30 by Saumya Chaturvedi, Aman Chadha, Chaturvedi, Saumya +3 · 1 citation
Computer Science · #Advanced Database Systems and Queries #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2509.00581

openalex publication_date 2025/08/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL
• A Study of In-Context-Learning-Based Text-to-SQL Errors
• CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
• Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios
• Text2SQL is Not Enough: Unifying AI and Databases with TAG
• A Survey on Employing Large Language Models for Text-to-SQL Tasks
• MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
• ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
• Exploring Chain-of-Thought Style Prompting for Text-to-SQL
• DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
• Reflexion: Language Agents with Verbal Reinforcement Learning
• RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL
• Towards Robustness of Text-to-SQL Models against Synonym Substitution
• Language Models are Few-Shot Learners
• Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

Cited by

• MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

Related

• ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought
• SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration
• RAISE: Reasoning Agent for Interactive SQL Exploration
• STaR-SQL: Self-Taught Reasoner for Text-to-SQL
• ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL