GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization
Summary: GPTuner uses LLMs to ingest DBMS manuals/forums and extract structured domain knowledge to drive workload-aware knob selection and value-range pruning. A prompt-ensemble plus coarse-to-fine Bayesian optimization finds configs 16× faster and up to 30% better (TPC-C/TPC-H on Postgres/MySQL). (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jiale Lao (Sichuan University)
- 2. Yibo Wang (Sichuan University)
- 3. Yufei Li (Sichuan University)
- 4. Jianping Wang (Northwest Normal University)
- 5. Yunjia Zhang (University of Wisconsin)
- 6. Zhiyuan Cheng (Purdue University)
- 7. Wanghu Chen (Northwest Normal University)
- 8. Mingjie Tang (Sichuan University)
- 9. Jianguo Wang (Purdue University)
BibTeX Citation
@article{lao_vldb24,
title = {{GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization}},
author = {Lao, Jiale and Wang, Yibo and Li, Yufei and Wang, Jianping and Zhang, Yunjia and Cheng, Zhiyuan and Chen, Wanghu and Tang, Mingjie and Wang, Jianguo},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {8},
pages = {1939--1952},
doi = {10.14778/3659437.3659449},
url = {https://doi.org/10.14778/3659437.3659449},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 29 of 29 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 26 of 26 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next