# QUITE: A Query Rewrite System Beyond Rules with LLM Agents arXiv: https://arxiv.org/abs/2506.07675 ยท HTML: https://mlsanity.com/paper/2506.07675/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 27 of its 83 references that are in the map. - First posted on arXiv 9 Jun 2025. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 27 of 27) - [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019) - [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023) - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023) - [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023) - [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023) - [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023) - [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023) - [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023) - [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023) - [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023) - [A Survey on Data Selection for Language Models](https://mlsanity.com/paper/2402.16827/) (2024) - [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024) - [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024) - [Neo: A Learned Query Optimizer](https://mlsanity.com/paper/1904.03711/) (2019) - [Bao: Learning to Steer Query Optimizers](https://mlsanity.com/paper/2004.03814/) (2020) - [Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency](https://mlsanity.com/paper/2309.17382/) (2023) - [GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization](https://mlsanity.com/paper/2311.03157/) (2023) - [Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources](https://mlsanity.com/paper/1802.10233/) (2018) - [A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1](https://mlsanity.com/paper/2502.10867/) (2025) - [LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency](https://mlsanity.com/paper/2404.12872/) (2024) - [R-Bot: An LLM-based Query Rewrite System](https://mlsanity.com/paper/2412.01661/) (2024) - [Large Language Models with Retrieval-Augmented Generation for Zero-Shot Disease Phenotyping](https://mlsanity.com/paper/2312.06457/) (2023) - [Can Large Language Models Be Query Optimizer for Relational Databases?](https://mlsanity.com/paper/2502.05562/) (2025) - [HoTTSQL: Proving Query Rewrites with Univalent SQL Semantics](https://mlsanity.com/paper/1607.04822/) (2016) - [Rewrite Rule Inference Using Equality Saturation](https://mlsanity.com/paper/2108.10436/) (2021) - [LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?](https://mlsanity.com/paper/2312.10321/) (2023) - [QueryBooster: Improving SQL Performance Using Middleware Services for Human-Centered Query Rewriting](https://mlsanity.com/paper/2305.08272/) (2023) ## Built on by (most cited first, 8 of 8) - [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025) - [DyFlow: Dynamic Workflow Framework for Agentic Reasoning](https://mlsanity.com/paper/2509.26062/) (2025) - [SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads](https://mlsanity.com/paper/2507.06192/) (2025) - [Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias](https://mlsanity.com/paper/2607.11871/) (2026) - [E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency](https://mlsanity.com/paper/2508.09023/) (2025) - [WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression](https://mlsanity.com/paper/2603.28809/) (2026) - [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026) - [Fail Loudly: An Auditable Runtime for Agentic Data Analysis](https://mlsanity.com/paper/2609.32528/) (2026) ## Abstract (arXiv) Query rewrite transforms SQL queries into semantically equivalent forms that run more efficiently. Existing approaches mainly rely on predefined rewrite rules, but they handle a limited subset of queries and can cause performance regressions. This limitation stems from three challenges of rule-based query rewrite: (1) it is hard to discover and verify new rules, (2) fixed rewrite rules do not generalize to new query patterns, and (3) some rewrite techniques cannot be expressed as fixed rules. Motivated by the fact that human experts exhibit significantly better rewrite ability but suffer from scalability, and Large Language Models (LLMs) have demonstrated nearly human-level semantic and reasoning abilities, we propose a new approach of using LLMs to rewrite SQL queries beyond rules. Due to the hallucination problems in LLMs, directly applying LLMs often leads to nonequivalent and suboptimal queries. To address this issue, we propose QUITE (query rewrite), a training-free and feedback-aware system based on LLM agents that rewrites SQL queries into semantically equivalent forms with significantly better performance, covering a broader range of query patterns and rewrite strategies compared to rule-based methods. Firstly, we design a multi-agent framework controlled by a finite state machine (FSM) to equip LLMs with the ability to use external tools and enhance the rewrite process with real-time database feedback. Secondly, we develop a rewrite middleware to enhance the ability of LLMs to generate optimized query equivalents. Finally, we employ a novel hint injection technique to improve execution plans for rewritten queries. Extensive experiments show that QUITE reduces query execution time by up to 35.8% over state-of-the-art approaches and produces 24.1% more rewrites than prior methods, covering query cases that earlier systems did not handle.