# Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL

arXiv: https://arxiv.org/abs/2504.15077 · HTML: https://mlsanity.com/paper/2504.15077/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 49 of its 74 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 49)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [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)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [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)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [Towards Robustness of Text-to-SQL Models against Synonym Substitution](https://mlsanity.com/paper/2106.01065/) (2021)

## Built on by (most cited first, 14 of 14)

- [VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use](https://mlsanity.com/paper/2509.01055/) (2025)
- [Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL](https://mlsanity.com/paper/2505.20315/) (2025)
- [CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning](https://mlsanity.com/paper/2505.13271/) (2025)
- [SLM-SQL: An Exploration of Small Language Models for Text-to-SQL](https://mlsanity.com/paper/2507.22478/) (2025)
- [MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL](https://mlsanity.com/paper/2510.25510/) (2025)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction](https://mlsanity.com/paper/2509.00581/) (2025)
- [SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation](https://mlsanity.com/paper/2509.25672/) (2025)
- [Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques](https://mlsanity.com/paper/2511.22258/) (2025)
- [Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL](https://mlsanity.com/paper/2512.22364/) (2025)
- [QueryGym: Step-by-Step Interaction with Relational Databases](https://mlsanity.com/paper/2509.21674/) (2025)
- [Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards](https://mlsanity.com/paper/2606.06825/) (2026)
- [From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection](https://mlsanity.com/paper/2601.18582/) (2026)
- [SQL-Zero: Self-Evolving Text-to-SQL](https://mlsanity.com/paper/2609.04697/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) can translate natural language into SQL, but small models struggle with multi-table and complex queries in Zero-Shot Learning (ZSL) settings. While Supervised Fine-Tuning (SFT) helps, it falls short for harder cases. To address this, we study how different reasoning strategies (general-purpose reasoning in ZSL, reasoning traces in SFT, and Reinforcement Learning with Verifiable Reward (RLVR) with novel reward functions) affect Text2SQL performance across four benchmarks. We show that partial scoring rewards, computed via SQL execution, are crucial for guiding models even when outputs are not fully correct. These fine-grained signals lead to consistently better Text2SQL outcomes. Small LLMs benefit most from reasoning-aware SFT and RL, with the 14B Qwen-Coder-2.5 surpassing 400B+ models on challenging datasets like BIRD.