Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
This addresses the problem of improving Text-to-SQL accuracy for database querying, representing a strong specific gain rather than a broad breakthrough.
The paper tackles the performance gap between state-of-the-art Text-to-SQL methods and human experts on challenging benchmarks like BIRD by introducing Agentar-Scale-SQL, which achieves 81.67% execution accuracy on the BIRD test set and ranks first on the official leaderboard.
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.