SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Hanwen, Zhang, Qihan, Marcus, Ryan, Sabek, Ibrahim
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914002569789440
author Liu, Hanwen
Zhang, Qihan
Marcus, Ryan
Sabek, Ibrahim
author_facet Liu, Hanwen
Zhang, Qihan
Marcus, Ryan
Sabek, Ibrahim
contents Query optimization is a crucial problem in database systems that has been studied for decades. Learned query optimizers (LQOs) can improve performance over time by incorporating feedback; however, they suffer from cold-start issues and often require retraining when workloads shift or schemas change. Recent LLM-based query optimizers leverage pre-trained and fine-tuned LLMs to mitigate these challenges. Nevertheless, they neglect LLMs' in-context learning and execution records as feedback for continuous evolution. In this paper, we present SEFRQO, a Self-Evolving Fine-tuned RAG-based Query Optimizer. SEFRQO mitigates the cold-start problem of LQOs by continuously learning from execution feedback via a Retrieval-Augmented Generation (RAG) framework. We employ both supervised fine-tuning and reinforcement fine-tuning to prepare the LLM to produce syntactically correct and performance-efficient query hints. Moreover, SEFRQO leverages the LLM's in-context learning capabilities by dynamically constructing prompts with references to similar queries and the historical execution record of the same query. This self-evolving paradigm iteratively optimizes the prompt to minimize query execution latency. Evaluations show that SEFRQO outperforms state-of-the-art LQOs, achieving up to 65.05% and 93.57% reductions in query latency on the CEB and Stack workloads, respectively, compared to PostgreSQL.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17556
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
Liu, Hanwen
Zhang, Qihan
Marcus, Ryan
Sabek, Ibrahim
Databases
Query optimization is a crucial problem in database systems that has been studied for decades. Learned query optimizers (LQOs) can improve performance over time by incorporating feedback; however, they suffer from cold-start issues and often require retraining when workloads shift or schemas change. Recent LLM-based query optimizers leverage pre-trained and fine-tuned LLMs to mitigate these challenges. Nevertheless, they neglect LLMs' in-context learning and execution records as feedback for continuous evolution. In this paper, we present SEFRQO, a Self-Evolving Fine-tuned RAG-based Query Optimizer. SEFRQO mitigates the cold-start problem of LQOs by continuously learning from execution feedback via a Retrieval-Augmented Generation (RAG) framework. We employ both supervised fine-tuning and reinforcement fine-tuning to prepare the LLM to produce syntactically correct and performance-efficient query hints. Moreover, SEFRQO leverages the LLM's in-context learning capabilities by dynamically constructing prompts with references to similar queries and the historical execution record of the same query. This self-evolving paradigm iteratively optimizes the prompt to minimize query execution latency. Evaluations show that SEFRQO outperforms state-of-the-art LQOs, achieving up to 65.05% and 93.57% reductions in query latency on the CEB and Stack workloads, respectively, compared to PostgreSQL.
title SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
topic Databases
url https://arxiv.org/abs/2508.17556