# The Unreasonable Effectiveness of LLMs for Query Optimization

arXiv: https://arxiv.org/abs/2411.02862 · HTML: https://mlsanity.com/paper/2411.02862/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 8 of 8)

- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [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)
- [Flow-Loss: Learning Cardinality Estimates That Matter](https://mlsanity.com/paper/2101.04964/) (2021)
- [Zero-Shot Cost Models for Distributed Stream Processing](https://mlsanity.com/paper/2207.03823/) (2022)

## Built on by (most cited first, 4 of 4)

- [LLM-Symbolic Integration for Robust Temporal Tabular Reasoning](https://mlsanity.com/paper/2506.05746/) (2025)
- [Training-Free Query Optimization via LLM-Based Plan Similarity](https://mlsanity.com/paper/2506.05853/) (2025)
- [LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization](https://mlsanity.com/paper/2507.03384/) (2025)
- [Bootstrapping Learned Cost Models with Synthetic SQL Queries](https://mlsanity.com/paper/2508.19807/) (2025)

## Abstract (arXiv)

Recent work in database query optimization has used complex machine learning strategies, such as customized reinforcement learning schemes. Surprisingly, we show that LLM embeddings of query text contain useful semantic information for query optimization. Specifically, we show that a simple binary classifier deciding between alternative query plans, trained only on a small number of labeled embedded query vectors, can outperform existing heuristic systems. Although we only present some preliminary results, an LLM-powered query optimizer could provide significant benefits, both in terms of performance and simplicity.