Pith. sign in

REVIEW 6 cited by

The Unreasonable Effectiveness of LLMs for Query Optimization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.02862 v1 pith:YLQQUJSC submitted 2024-11-05 cs.DB cs.LG

Peter Akioyamen , Zixuan Yi , Ryan Marcus This is my paper
classification cs.DBcs.LG
keywords queryoptimizationlearningonlyalternativealthoughbenefitsbinary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling

    cs.DB 2026-06 conditional novelty 7.0 of 10

    ReSequel uses LLMs guided by metadata-derived templates and sampling-based verification to rewrite SQL queries, delivering up to 16x workload speedups over native DBMSs and 22x over prior LLM baselines across eight be...

  2. Evaluating the Practical Effectiveness of LLM-Driven Index Tuning on Microsoft SQL Server

    cs.DB 2026-03 unverdicted novelty 6.0 of 10

    LLMs can outperform DTA on index recommendations for some workloads but remain less reliable with practical adoption challenges.

  3. MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration

    cs.DB 2025-09 reject novelty 5.0 of 10

    MCTuner reports up to 19.2% performance gains and roughly 1.4x faster discovery of good configurations by combining LLM knob selection with recursive space decomposition and Bayesian optimization.

  4. Bootstrapping Learned Cost Models with Synthetic SQL Queries

    cs.DB 2025-08 conditional novelty 5.0 of 10

    LLM-based synthetic SQL generation can train a learned cost model with fewer, more diverse queries than mechanical generation, though the measured accuracy gains are small and the comparison is not matched by training size.

  5. Training-Free Query Optimization via LLM-Based Plan Similarity

    cs.DB 2025-06 conditional novelty 5.0 of 10

    LLM-PM, a training-free system that transfers optimizer hints from nearest-neighbour LLM plan embeddings, reports a 21.1% total runtime reduction on JOB-CEB over openGauss.

  6. A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads

    cs.DB 2025-06 conditional novelty 5.0 of 10

    A multi-head learned cost model with a shared graph-neural-network embedding routes SQL queries to the fastest engine in a lakehouse, using Calcite-optimized logical plans as inputs.

Pith tools