AGRO-SQL: Agentic Group-Relative Optimization with High-Fidelity Data Synthesis
This addresses data and reasoning bottlenecks for Text-to-SQL systems, representing an incremental improvement.
The paper tackles the problem of Text-to-SQL systems hindered by scarce high-quality training data and limited reasoning in complex scenarios, achieving state-of-the-art performance on BIRD and Spider benchmarks.
The advancement of Text-to-SQL systems is currently hindered by the scarcity of high-quality training data and the limited reasoning capabilities of models in complex scenarios. In this paper, we propose a holistic framework that addresses these issues through a dual-centric approach. From a Data-Centric perspective, we construct an iterative data factory that synthesizes RL-ready data characterized by high correctness and precise semantic-logic alignment, ensured by strict verification. From a Model-Centric perspective, we introduce a novel Agentic Reinforcement Learning framework. This framework employs a Diversity-Aware Cold Start stage to initialize a robust policy, followed by Group Relative Policy Optimization (GRPO) to refine the agent's reasoning via environmental feedback. Extensive experiments on BIRD and Spider benchmarks demonstrate that our synergistic approach achieves state-of-the-art performance among single-model methods.