Iteration Without Elaboration: A Simple ReAct Architecture Suffices for Text-to-SQL Generation

2026-08-23

AI Summary

研究提出ReAct-SQL框架，通过迭代推理和限定的动作空间解决文本到SQL生成问题，简化了现有系统并提高了效率。

Abstract

Modern text-to-SQL systems have become increasingly elaborate, relying on schema-linking modules, retrieval-augmented prompting, candidate generation, and multi-stage refinement pipelines. While effective, these additions introduce substantial latency and engineering overhead. To this end, we present \textbf{ReAct-SQL}, a simple yet effective zero-shot ReAct-style framework built solely on iterative reasoning and a constrained action space defined by a typed Domain-Specific Language (DSL) of 15 relational operations, rather than free-form SQL generation. The model incrementally issues DSL calls, observes compiled-SQL execution feedback, and revises its reasoning through interaction. On corrected BIRD mini-dev and EHR-SQL, ReAct-SQL achieves \textbf{84.5\%} and \textbf{73.9\%} accuracy, respectively, matching substantially more elaborate baselines while running up to $8\times$ faster. Incremental ablations further show that iteration primarily improves grounding, while the DSL improves compositional reliability.

Problem

• text-to-SQL
• schema-linking
• retrieval-augmented prompting
• multi-stage refinement

Innovation

• ReAct-SQL
• iterative reasoning
• typed Domain-Specific Language (DSL)
• zero-shot framework
• text-to-SQL generation