# Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration arXiv: https://arxiv.org/abs/2508.15809 ยท HTML: https://mlsanity.com/paper/2508.15809/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 42 of its 57 references that are in the map. - First posted on arXiv 14 Aug 2025. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 30 of 42) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023) - [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023) - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023) - [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018) - [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023) - [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015) - [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023) - [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020) - [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019) - [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023) - [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022) - [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024) - [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024) - [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023) - [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021) - [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023) - [Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources](https://mlsanity.com/paper/2305.13269/) (2023) - [Data-efficient Fine-tuning for LLM-based Recommendation](https://mlsanity.com/paper/2401.17197/) (2024) - [ReAcTable: Enhancing ReAct for Table Question Answering](https://mlsanity.com/paper/2310.00815/) (2023) - [Exploring Chain-of-Thought Style Prompting for Text-to-SQL](https://mlsanity.com/paper/2305.14215/) (2023) - [Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments](https://mlsanity.com/paper/2212.09736/) (2022) - [Generative Table Pre-training Empowers Models for Tabular Prediction](https://mlsanity.com/paper/2305.09696/) (2023) - [Large Language Model for Table Processing: A Survey](https://mlsanity.com/paper/2402.05121/) (2024) - [TableRAG: Million-Token Table Understanding with Language Models](https://mlsanity.com/paper/2410.04739/) (2024) - [Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table](https://mlsanity.com/paper/2305.07288/) (2023) - [TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition](https://mlsanity.com/paper/2404.10150/) (2024) - [TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation](https://mlsanity.com/paper/2406.10450/) (2024) - [TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning](https://mlsanity.com/paper/2312.09039/) (2023) - [StructLM: Towards Building Generalist Models for Structured Knowledge Grounding](https://mlsanity.com/paper/2402.16671/) (2024) ## Built on by (most cited first, 6 of 6) - [Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning](https://mlsanity.com/paper/2509.02401/) (2025) - [Training-Free Time Series Classification via In-Context Reasoning with LLM Agents](https://mlsanity.com/paper/2510.05950/) (2025) - [Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows](https://mlsanity.com/paper/2607.07504/) (2026) - [SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis](https://mlsanity.com/paper/2604.21414/) (2026) - [Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation](https://mlsanity.com/paper/2610.02353/) (2026) - [Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness](https://mlsanity.com/paper/2610.04792/) (2026) ## Abstract (arXiv) 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.