Prompting Strategies for Enterprise Text-to-SQL: An Ablation Study

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

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.

Prompt Template-Driven Large Model SQL Generation

GradeSQL: Outcome reward models for intelligent Text-to-SQL generation from LLMs

As Large Language Models (LLMs) become foundational to next-generation Intelligent Information Systems, the bridge between natural language interfaces and structured database systems remains a critical bottleneck. While Text-to-SQL generation enables cooperative support for complex query formulation, ensuring the reliability of these generated queries at inference time is a central challenge. Conventional methods rely on coarse execution-based signals, which may limit their ability to capture the nuanced semantic alignment required for high-stakes database environments. In this work, we propose the use of Outcome Reward Models (ORMs) as a fine-grained, probabilistic feedback mechanism for test-time verification in Text-to-SQL tasks. We introduce GradeSQL, a framework for training task-specific ORMs that assign scalar utility scores to candidate SQL queries based on their semantic correctness and alignment with database schema. Our approach is evaluated on the BIRD and Spider benchmarks across multiple open-source LLM families. Experimental results demonstrate that ORM-based verification consistently outperforms traditional execution-based heuristics.

SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation

SQuaD-SQL (Small-Qualified and Distilled for SQL), a novel approach that empowers small language models to approach the performance of LLMs on the Text-to-SQL task while significantly improving efficiency through knowledge distillation and synthetic data generation, is introduced.

Text-to-SQL with Large Language Models: Challenges Revisited and New Dimensions

This position paper argues that each original challenge for LLM-based Text-to-SQL has given rise to a new dimension, and synthesizes these concerns and outlines a research agenda along three horizons, arguing for trustworthiness, interactivity, and economic sustainability as first-class concerns.

ExpeSQL: An Efficient, Experience-Guided Decompositional Search Framework for Text-to-SQL

This work introduces ExpeSQL, a zero-shot, open-source–compatible, and efficient framework that combines divide-and-conquer reasoning, Best-of-N candidate selection, and self-critique with experience-guided refinement that establishes a new paradigm for deployable, self-improving Text-to-SQL systems in dynamic, real-world environments.