Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909952564527104 |
|---|---|
| author | Wang, Pengfei Sun, Baolin Dong, Xuemei Dai, Yaxun Yuan, Hongwei Chu, Mengdie Gao, Yingqi Qi, Xiang Zhang, Peng Yan, Ying |
| author_facet | Wang, Pengfei Sun, Baolin Dong, Xuemei Dai, Yaxun Yuan, Hongwei Chu, Mengdie Gao, Yingqi Qi, Xiang Zhang, Peng Yan, Ying |
| contents | State-of-the-art (SOTA) Text-to-SQL methods still lag significantly behind human experts on challenging benchmarks like BIRD. Current approaches that explore test-time scaling lack an orchestrated strategy and neglect the model's internal reasoning process. To bridge this gap, we introduce Agentar-Scale-SQL, a novel framework leveraging scalable computation to improve performance. Agentar-Scale-SQL implements an Orchestrated Test-Time Scaling strategy that synergistically combines three distinct perspectives: i) Internal Scaling via RL-enhanced Intrinsic Reasoning, ii) Sequential Scaling through Iterative Refinement, and iii) Parallel Scaling using Diverse Synthesis and Tournament Selection. Agentar-Scale-SQL is a general-purpose framework designed for easy adaptation to new databases and more powerful language models. Extensive experiments show that Agentar-Scale-SQL achieves SOTA performance on the BIRD benchmark, reaching 81.67% execution accuracy on the test set and ranking first on the official leaderboard, demonstrating an effective path toward human-level performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24403 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling Wang, Pengfei Sun, Baolin Dong, Xuemei Dai, Yaxun Yuan, Hongwei Chu, Mengdie Gao, Yingqi Qi, Xiang Zhang, Peng Yan, Ying Computation and Language Databases State-of-the-art (SOTA) Text-to-SQL methods still lag significantly behind human experts on challenging benchmarks like BIRD. Current approaches that explore test-time scaling lack an orchestrated strategy and neglect the model's internal reasoning process. To bridge this gap, we introduce Agentar-Scale-SQL, a novel framework leveraging scalable computation to improve performance. Agentar-Scale-SQL implements an Orchestrated Test-Time Scaling strategy that synergistically combines three distinct perspectives: i) Internal Scaling via RL-enhanced Intrinsic Reasoning, ii) Sequential Scaling through Iterative Refinement, and iii) Parallel Scaling using Diverse Synthesis and Tournament Selection. Agentar-Scale-SQL is a general-purpose framework designed for easy adaptation to new databases and more powerful language models. Extensive experiments show that Agentar-Scale-SQL achieves SOTA performance on the BIRD benchmark, reaching 81.67% execution accuracy on the test set and ranking first on the official leaderboard, demonstrating an effective path toward human-level performance. |
| title | Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling |
| topic | Computation and Language Databases |
| url | https://arxiv.org/abs/2509.24403 |