E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency

2025-08-12

AI Summary

Existing rule-based SQL rewriting approaches suffer from poor generalizability and fail to handle complex queries or capture implicit optimization strategies. To address this, we propose the first LLM-based SQL rewriting framework jointly driven by execution awareness and semantic alignment. Our method constructs context-aware prompts using query execution plans and exemplars, integrates syntax validation, semantic equivalence verification, and cost estimation modules, and employs a three-stage curriculum-style reinforcement learning strategy to jointly optimize for execution time, semantic equivalence, and rewriting success rate. Evaluated on multiple benchmarks, our framework achieves an average 25.6% reduction in execution time and a 24.4% improvement in rewriting success rate, demonstrating significantly enhanced modeling and optimization capability for complex SQL queries.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Language Models
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

SQL query rewriting aims to reformulate a query into a more efficient form while preserving equivalence. Most existing methods rely on predefined rewrite rules. However, such rule-based approaches face fundamental limitations: (1) fixed rule sets generalize poorly to novel query patterns and struggle with complex queries; (2) a wide range of effective rewriting strategies cannot be fully captured by declarative rules. To overcome these issues, we propose using large language models (LLMs) to generate rewrites. LLMs can capture complex strategies, such as evaluation reordering and CTE rewriting. Despite this potential, directly applying LLMs often results in suboptimal or non-equivalent rewrites due to a lack of execution awareness and semantic grounding. To address these challenges, We present E3-Rewrite, an LLM-based SQL rewriting framework that produces executable, equivalent, and efficient queries. It integrates two core components: a context construction module and a reinforcement learning framework. First, the context module leverages execution plans and retrieved demonstrations to build bottleneck-aware prompts that guide inference-time rewriting. Second, we design a reward function targeting executability, equivalence, and efficiency, evaluated via syntax checks, equivalence verification, and cost estimation. Third, to ensure stable multi-objective learning, we adopt a staged curriculum that first emphasizes executability and equivalence, then gradually incorporates efficiency. Extensive experiments show that E3-Rewrite achieves up to a 25.6% reduction in query execution time compared to state-of-the-art methods across multiple SQL benchmarks. Moreover, it delivers up to 24.4% more successful rewrites, expanding coverage to complex queries that previous systems failed to handle.

Problem

• Overcoming limitations of rule-based SQL query rewriting methods
• Ensuring executable, equivalent, and efficient SQL rewrites using LLMs
• Addressing suboptimal rewrites via execution-aware context and reinforcement learning

Innovation

• LLM-based SQL rewriting for efficiency and equivalence
• Context module with execution-aware prompting
• Reinforcement learning with staged curriculum