Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling

📝 Introduction

Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance on challenging benchmarks. By implementing an Orchestrated Test-Time Scaling strategy, our framework synergistically combines three distinct perspectives to bridge the gap between state-of-the-art models and human expert performance.

🎉 News

• 🎁 2025.09.30: Our paper is available on arXiv.
• 🎁 2025.09.25: 🏆 We have achieved #1 Rank on the official BIRD leaderboard with 81.67% execution accuracy!

🗺️ Release Roadmap

We are committed to continuously improving Agentar-Scale-SQL. Here is our plan for upcoming features and releases.

• Paper
  • [x] Publish the paper on arXiv.
• Model Releases
  • [ ] Release Agentar-Scale-SQL-Generation-32B on Hugging Face and ModelScope.
  • [ ] Release Agentar-Scale-SQL-Selection-32B on Hugging Face and ModelScope.
• Code Releases
  • [ ] Release the code for the light schema engine.
  • [ ] Release the code for the offline data preprocessing pipeline.
  • [ ] Release the code for task understanding and generating SQL candidates with closed-source models.
  • [ ] Release the code for generating SQL candidates with the fine-tuned model.
  • [ ] Release the code for the SQL selection module.

🏛 License

This framework is licensed under the Apache License (Version 2.0).

📎 Citation

@misc{wang2025agentarscalesqladvancingtexttosqlorchestrated,
      title={Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling}, 
      author={Pengfei Wang and Baolin Sun and Xuemei Dong and Yaxun Dai and Hongwei Yuan and Mengdie Chu and Yingqi Gao and Xiang Qi and Peng Zhang and Ying Yan},
      year={2025},
      eprint={2509.24403},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.24403}, 
}