Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration

Abstract: Table understanding requires structured, multi-step reasoning. 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. Experiments with four models (both closed- and open-source) across five widely used benchmarks show that Chain-of-Query significantly improves accuracy from 61.11% to 74.77% and reduces the invalid SQL rate from 9.48% to 3.34%, demonstrating its superior effectiveness in table understanding. The code is available at https://github.com/SongyuanSui/ChainofQuery.