Natural Language to SQL (NL2SQL) enables intuitive interactions with databases by transforming natural language queries into structured SQL statements. Despite recent advancements in enhancing human-computer interaction within database applications, significant challenges persist, particularly regarding the inference performance in complex scenarios involving multi-table joins and nested queries. Current methodologies primarily utilize supervised fine-tuning (SFT) to train the NL2SQL model, which may limit adaptability and interpretability in new environments (e.g., finance and healthcare). In order to enhance the reasoning performance of the NL2SQL model in the above complex situations, we introduce SQL-R1, a novel NL2SQL reasoning model trained by the reinforcement learning (RL) algorithms. We design a specialized RL-based reward function tailored for NL2SQL tasks and discussed the impact of cold start on the effectiveness of intensive training. In addition, we achieve competitive accuracy using only a tiny amount of synthetic NL2SQL data for augmented training and further explore data engineering for RL. In existing experiments, SQL-R1 achieves execution accuracy of 88.6% and 67.1% on the benchmark Spider and BIRD, respectively.

Figure 1: Demonstration of our work.

@article{ma2025sql,
  title={SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning},
  author={Ma, Peixian and Zhuang, Xialie and Xu, Chengjin and Jiang, Xuhui and Chen, Ran and Guo, Jian},
  journal={arXiv preprint arXiv:2504.08600},
  year={2025}
}

• [2025.09.18] 🎉 SQL-R1 is accept by NeurIPS 2025! We will soon update the full version of the paper and poster. Welcome to star and cite our work!
• [2025.05.27] 🎉 We have released the full version of SQL-R1.
• [2025.05.21] 🎉 We have released our model weights on HuggingFace! Check out the Model Weights section below.
• [2025.04.11] 📑 Our paper is now available on arXiv.

• 📝 Update the camera-ready version of the paper, homepage and poster. coming sooooon!
• 📊 Release model weights on HuggingFace and ModelScope
• 🔧 Open source training code and RL dataset
• 📝 Detailed documentation
• 🛠️ Environment setup guide

We are excited to release our SQL-R1 model weights! You can find them on HuggingFace:

This repository is organized as follows:

SQL-R1/
├── 📁 data/                             # Datasets and Databases
│   ├── 📁 Spider/      
│   └── 📁 BIRD/        
├── 📁 models/                           # Foundation models or checkpoints
│   ├── 📁 Qwen2.5-Coder-3B-Instruct/   
│   └── 📁 Qwen2.5-Coder-7B-Instruct/   
├── 📁 db_info/                          # Database information files (Just for inference)
├── 📁 example_data/                     # Example data (Training)
├── 📁 sh/                               # Scripts for data processing, training, inference and evaluation
│   ├── 📄 train.sh
│   ├── 📄 inference.sh
│   ├── 📄 eval_spider.sh
│   └── 📄 eval_bird.sh
├── 📁 src/                              # Source code
│   ├── 📁 data_preprocess/
│   ├── 📁 evaluations/
│   ├── 📁 utils/
│   ├── 📄 inference.py
│   └── 📄 evaluation_*.py
├── 📁 verl/                             # Verl reinforcement learning framework
├── 📄 requirements.txt
└── 📄 README.md

1. Clone the repository:

git clone https://github.com/MPX0222/SQL-R1.git
cd SQL-R1

2. Create and activate a virtual environment (recommended):

conda create -n sqlr1 python=3.9

3. Install dependencies:

pip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu121
pip install vllm==0.6.3 ray
pip install flash-attn --no-build-isolation
pip install -e .  # For verl integration
pip install wandb IPython matplotlib sqlparse func_timeout nltk ijson

4. Download the model weights from HuggingFace and put them in the models/ directory.

5. For training, copy the training dataset in the example_data directory to the data directory. For inference, copy the database information in the db_info directory (including files forSpider-dev, Spider-test and BIRD-dev) to the related dataset (data/Spider, data/BIRD) directory.

1. Run training:

sh sh/train.sh

2. Run inference:

sh sh/inference.sh

3. Run evaluation:

# evaluate spider
sh sh/eval_spider.sh
# evaluate bird
sh sh/eval_bird.sh

SQL-R1 can be effectively utilized in the following key areas:

1. Foundation Model for Workflow Systems

   • Serves as a base model for complex database operations
   • Enables seamless integration with existing workflow automation systems
   • Supports customization and fine-tuning for specific business processes
   • Provides robust API endpoints for system integration

2. Enhanced NL2SQL Interpretability

   • Generates detailed explanations for SQL query construction
   • Provides step-by-step reasoning for query transformation
   • Helps users understand the relationship between natural language and SQL syntax
   • Offers visualization of query execution plans

3. Self-Evolving NL2SQL Agent Checkpoint

   • Acts as a foundation checkpoint for continuous learning
   • Enables iterative improvement through feedback loops
   • Supports transfer learning for domain-specific adaptations
   • Facilitates model versioning and performance tracking

This may be added in the future work. If you have any ideas, please feel free to contact us.

We thank OmniSQL and follow their evaluation code and database information retrieval code. We have adapted and modified their evaluation scripts for our project.