# Training-Free Query Optimization via LLM-Based Plan Similarity

arXiv: https://arxiv.org/abs/2506.05853 · HTML: https://mlsanity.com/paper/2506.05853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [Neo: A Learned Query Optimizer](https://mlsanity.com/paper/1904.03711/) (2019)
- [Learned Cardinalities: Estimating Correlated Joins with Deep Learning](https://mlsanity.com/paper/1809.00677/) (2018)
- [Bao: Learning to Steer Query Optimizers](https://mlsanity.com/paper/2004.03814/) (2020)
- [Lero: A Learning-to-Rank Query Optimizer](https://mlsanity.com/paper/2302.06873/) (2023)
- [LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency](https://mlsanity.com/paper/2404.12872/) (2024)
- [Can Large Language Models Be Query Optimizer for Relational Databases?](https://mlsanity.com/paper/2502.05562/) (2025)
- [COOOL: A Learning-To-Rank Approach for SQL Hint Recommendations](https://mlsanity.com/paper/2304.04407/) (2023)
- [The Unreasonable Effectiveness of LLMs for Query Optimization](https://mlsanity.com/paper/2411.02862/) (2024)
- [HERO: Hint-Based Efficient and Reliable Query Optimizer](https://mlsanity.com/paper/2412.02372/) (2024)
- [Adaptive Cost Model for Query Optimization](https://mlsanity.com/paper/2409.17136/) (2024)

## Abstract (arXiv)

Large language model (LLM) embeddings offer a promising new avenue for database query optimization. In this paper, we explore how pre-trained execution plan embeddings can guide SQL query execution without the need for additional model training. We introduce LLM-PM (LLM-based Plan Mapping), a framework that embeds the default execution plan of a query, finds its k nearest neighbors among previously executed plans, and recommends database hintsets based on neighborhood voting. A lightweight consistency check validates the selected hint, while a fallback mechanism searches the full hint space when needed. Evaluated on the JOB-CEB benchmark using OpenGauss, LLM-PM achieves an average speed-up of 21% query latency reduction. This work highlights the potential of LLM-powered embeddings to deliver practical improvements in query performance and opens new directions for training-free, embedding-based optimizer guidance systems.