DBScholar

Back to papers

Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents

Summary: SysInsight combines static analysis and LLM reasoning to mine DBMS source code for knob-controlled execution paths and fine-grained tuning insights, converting them into verifiable rules via association mining. It reaches optimal configurations 7.11× faster and improves performance 19.9%. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
ha5cc72e952fe0b8e
Venue
VLDB
Year
2026
Pagerank
5.0407989e-05
Overall Rank
10,297 | 30.80%
DOI
10.14778/3797919.3797940
PDF
Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{zhang_vldb26,
        title = {{Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents}},
        author = {Zhang, Xinyi and Chen, Tiantian and Han, Zhentao and Hong, Zhaoyan and Lu, Wei and Wang, Sheng and Sha, Mo and Wang, Anni and Liu, Shuang and Zhang, Yakun and Li, Feifei and Du, Xiaoyong},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {6},
        pages = {1358--1371},
        doi = {10.14778/3797919.3797940},
        url = {https://doi.org/10.14778/3797919.3797940},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank Citing Paper Year Venue Pagerank
10,444 DBugScribe: Automatic Database Bug Reproduction from Community Reports 2026 SIGMOD 4.9769913e-05
10,950 Ultron: History-Based Query Optimization at Databricks 2026 VLDB 4.9769913e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 24 of 24 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
13 Mining Association Rules between Sets of Items in Large Databases 1993 SIGMOD 0.00064391979
78 Automatic Database Management System Tuning Through Large-scale Machine Learning 2017 SIGMOD 0.00036675568
235 OLTP-Bench: An Extensible Testbed for Benchmarking Relational Databases 2014 VLDB 0.00023689995
314 An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning 2019 SIGMOD 0.00021276452
322 Tuning Database Configuration Parameters with iTuned 2009 VLDB 0.00021034201
437 QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning 2019 VLDB 0.00018310278
461 Query-based Workload Forecasting for Self-Driving Database Management Systems 2018 SIGMOD 0.00017841988
492 Database Tuning Advisor for Microsoft SQL Server 2005 2004 VLDB 0.00017406029
508 Adaptive Self-Tuning Memory in DB2 2006 VLDB 0.00017083245
781 Self-tuning Database Technology and Information Services: from Wishful Thinking to Viable Engineering 2002 VLDB 0.00014019939
1,245 DB-BERT: A Database Tuning Tool that "Reads the Manual" 2022 SIGMOD 0.0001136308
1,289 An Inquiry into Machine Learning-based Automatic Configuration Tuning Services on Real-World Database Management Systems 2021 VLDB 0.00011159167
2,227 GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization 2024 VLDB 8.8007923e-05
2,721 ResTune: Resource Oriented Tuning Boosted by Meta-Learning for Cloud Databases 2021 SIGMOD 8.0931221e-05
2,770 Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation 2022 VLDB 8.0343719e-05
3,052 LlamaTune: Sample-Efficient DBMS Configuration Tuning 2022 VLDB 7.704739e-05
3,159 CGPTuner: a Contextual Gaussian Process Bandit Approach for the Automatic Tuning of IT Configurations Under Varying Workload Conditions 2021 VLDB 7.5797912e-05
3,352 Database Tuning: principles, experiments, and troubleshooting techniques 2002 SIGMOD 7.3871134e-05
3,487 HUNTER: An Online Cloud Database Hybrid Tuning System for Personalized Requirements 2022 SIGMOD 7.2603973e-05
3,648 UDO: Universal Database Optimization using Reinforcement Learning 2021 VLDB 7.1366536e-05
4,080 Towards Dynamic and Safe Configuration Tuning for Cloud Databases 2022 SIGMOD 6.8151596e-05
5,284 An Efficient Transfer Learning Based Configuration Adviser for Database Tuning 2024 VLDB 6.1963031e-05
6,254 Foundations of Automated Database Tuning 2006 VLDB 5.8328094e-05
7,794 Database Tuning 1992 VLDB 5.4505168e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 6,732 A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning 2023 SIGMOD
2 7,072 E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model 2025 VLDB
3 1,289 An Inquiry into Machine Learning-based Automatic Configuration Tuning Services on Real-World Database Management Systems 2021 VLDB
4 10,591 MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration 2026 SIGMOD
5 3,052 LlamaTune: Sample-Efficient DBMS Configuration Tuning 2022 VLDB
6 3,171 Panda: Performance Debugging for Databases using LLM Agents 2024 CIDR
7 78 Automatic Database Management System Tuning Through Large-scale Machine Learning 2017 SIGMOD
8 10,296 This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch! 2026 SIGMOD
9 2,227 GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization 2024 VLDB
10 9,911 AgentTune: An Agent-Based Large Language Model Framework for Database Knob Tuning 2026 SIGMOD