Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks
Yihan Wang, Peiyu Liu, Runyu Chen, Jiaxing Pu, Wei Xu
TL;DR
Squrve tackles the gap between research and production in Text-to-SQL by standardizing interfaces and enabling cross-method collaboration. Squrve provides a universal execution paradigm, a four-module architecture (Data, Actor, Task, Execution), and seven atomic actors with a Pipeline/Tree collaboration mechanism that yields ensemble benefits, e.g., $SQL = f_{\text{actor}}(Q, S, C|M)$. On Spider and Bird benchmarks, Squrve reproduces existing baselines with comparable accuracy and demonstrates that ensemble workflows outperform single models in $EX$. The framework offers a practical pathway to deploy robust, real-world Text-to-SQL systems by decoupling capabilities from usage and supporting reusable components.
Abstract
Text-to-SQL technology has evolved rapidly, with diverse academic methods achieving impressive results. However, deploying these techniques in real-world systems remains challenging due to limited integration tools. Despite these advances, we introduce Squrve, a unified, modular, and extensive Text-to-SQL framework designed to bring together research advances and real-world applications. Squrve first establishes a universal execution paradigm that standardizes invocation interfaces, then proposes a multi-actor collaboration mechanism based on seven abstracted effective atomic actor components. Experiments on widely adopted benchmarks demonstrate that the collaborative workflows consistently outperform the original individual methods, thereby opening up a new effective avenue for tackling complex real-world queries. The codes are available at https://github.com/Satissss/Squrve.