Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration
This work addresses table understanding for users needing reliable SQL queries from complex tabular data, representing an incremental advance over prior multi-agent methods.
The paper tackles the problem of table understanding by addressing limitations in existing multi-agent SQL generation frameworks, such as error propagation and over-reliance on execution correctness, and proposes Chain-of-Query (CoQ), which achieves substantial accuracy improvements and significantly lowers invalid SQL rates across multiple benchmarks.
Table understanding requires structured, multi-step reasoning. Large Language Models (LLMs) struggle with it due to the structural complexity of tabular data. Recently, multi-agent frameworks for SQL generation have shown promise in tackling the challenges of understanding tabular data, but existing approaches often suffer from limitations such as the inability to comprehend table structure for reliable SQL generation, error propagation that results in invalid queries, and over-reliance on execution correctness. To address these issues, we propose Chain-of-Query (CoQ), a novel multi-agent framework for SQL-aided table understanding. CoQ adopts natural-language-style representations of table schemas to abstract away structural noise and enhance understanding. It employs a clause-by-clause SQL generation strategy to improve query quality and introduces a hybrid reasoning division that separates SQL-based mechanical reasoning from LLM-based logical inference, thereby reducing reliance on execution outcomes. Extensive experiments across four models and five widely used benchmarks demonstrate that CoQ achieves substantial accuracy improvements and significantly lowers invalid SQL rates compared to prior generic LLM-based, SQL-aided, and hybrid baselines, confirming its superior effectiveness in table understanding. The code is available at https://github.com/SongyuanSui/ChainofQuery.