LASER: A Data-Centric Method for Low-Cost and Efficient SQL Rewriting based on SQL-GRPO

TL;DR

LASER introduces a data-centric framework that enables small language models to perform efficient SQL query rewriting, significantly improving execution performance with minimal overhead.

Contribution

The paper develops SQL-GRPO and constructs SQL-MCTS to train small models for robust, execution-aware SQL optimization, addressing data scarcity and efficiency challenges.

Findings

LASER outperforms rule-based and LLM approaches in execution efficiency.

Constructed SQL-MCTS with a hybrid expansion strategy for complex slow queries.

LASER demonstrates strong zero-shot transferability with minimal overhead.

Abstract

Query rewriting, the process of transforming queries into semantically equivalent yet more efficient variants, is crucial for database optimization. Existing solutions predominantly rely on either rule-based heuristics or Large Language Models (LLMs). However, traditional rule-based methods lack adaptability, while LLM-based approaches incur prohibitive inference costs and privacy risks. In contrast, Small Language Models (SLMs) present a compelling middle ground, potentially offering both flexibility and efficiency. However, the development of such compact models is severely bottlenecked by the scarcity of high-quality, domain-specific training data. To bridge this gap, we introduce LASER, a data-centric framework designed to empower small models for robust SQL optimization. First, to address the scarcity of existing benchmarks and the limited optimization headroom of generic synthetic queries, we construct SQL-MCTS, a large-scale corpus of complex slow queries. We employ an MCTS-based hybrid expansion strategy that combines rule-guided anti-patterns with LLM mutations to evolve structurally expressive seeds into execution-verified slow variants. Second, to enable the model to autonomously discover latency-aware rewriting patterns, we propose SQL-GRPO, a specialized alignment strategy adapted from Group Relative Policy Optimization. By integrating Anchored Group Advantage to refine advantage estimation and Complexity-Adaptive Dynamic Rollout to efficiently allocate exploration budgets, this approach effectively empowers compact models to master execution-based optimization logic. Implemented on Qwen3 models, LASER significantly outperforms rule-based systems and LLMs in execution efficiency, while exhibiting robust zero-shot transferability with minimal overhead.