DBScholar

Back to papers

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

Summary: Empirical study of LLM-based index tuning for SQL Server across benchmarks and enterprise workloads, compared with DTA. LLMs sometimes achieve substantially faster execution, but exhibit high variance and often worse optimizer-estimated costs, complicating hybrid advisors. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID
h9ee2968f11257219
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,918 | 26.60%
DOI
10.14778/3827998.3828015

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{wang_vldb26,
        title = {{Evaluating the Practical Effectiveness of LLM-Driven Index Tuning on Microsoft SQL Server}},
        author = {Wang, Xiaoying and Wu, Wentao and Narasayya, Vivek and Chaudhuri, Surajit},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {12},
        pages = {4049--4062},
        doi = {10.14778/3827998.3828015},
        url = {https://doi.org/10.14778/3827998.3828015},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 42 of 42 cited papers.

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

Rank Cited Paper Year Venue Pagerank
15 How Good Are Query Optimizers, Really? 2016 VLDB 0.00061066921
78 Automatic Database Management System Tuning Through Large-scale Machine Learning 2017 SIGMOD 0.00036684414
91 On the Propagation of Errors in the Size of Join Results 1991 SIGMOD 0.0003475226
151 An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server 1997 VLDB 0.00028672526
314 An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning 2019 SIGMOD 0.00021282642
322 Tuning Database Configuration Parameters with iTuned 2009 VLDB 0.00021041865
378 AutoAdmin "What-if" Index Analysis Utility 1998 SIGMOD 0.00019549382
437 QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning 2019 VLDB 0.00018315867
491 Database Tuning Advisor for Microsoft SQL Server 2005 2004 VLDB 0.00017413042
560 Plan-Structured Deep Neural Network Models for Query Performance Prediction 2019 VLDB 0.00016403151
751 Automatic Physical Database Tuning: A Relaxation-based Approach 2005 SIGMOD 0.0001425375
1,064 Are We Ready For Learned Cardinality Estimation? 2021 VLDB 0.00012202282
1,242 Compressing SQL Workloads 2002 SIGMOD 0.00011373611
1,257 Sampling-Based Query Re-Optimization 2016 SIGMOD 0.00011310561
1,279 AI Meets AI: Leveraging Query Executions to Improve Index Recommendations 2019 SIGMOD 0.00011226878
1,289 An Inquiry into Machine Learning-based Automatic Configuration Tuning Services on Real-World Database Management Systems 2021 VLDB 0.00011162479
1,397 Magic mirror in my hand, which is the best in the land? An Experimental Evaluation of Index Selection Algorithms 2020 VLDB 0.00010789242
1,516 Automatically Indexing Millions of Databases in Microsoft Azure SQL Database 2019 SIGMOD 0.00010402594
1,658 D-Bot: Database Diagnosis System using Large Language Models 2024 VLDB 9.9642078e-05
1,815 CoPhy: A Scalable, Portable, and Interactive Index Advisor for Large Workloads 2011 VLDB 9.5791737e-05
2,039 LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency 2025 VLDB 9.1493268e-05
2,275 Active Learning for ML Enhanced Database Systems 2020 SIGMOD 8.7090584e-05
3,051 LlamaTune: Sample-Efficient DBMS Configuration Tuning 2022 VLDB 7.7055931e-05
3,158 CGPTuner: a Contextual Gaussian Process Bandit Approach for the Automatic Tuning of IT Configurations Under Varying Workload Conditions 2021 VLDB 7.5811757e-05
3,336 GenRewrite: Query Rewriting via Large Language Models 2026 SIGMOD 7.4137763e-05
3,815 Comprehensive and Efficient Workload Compression 2021 VLDB 7.0075744e-05
4,385 R-Bot: An LLM-based Query Rewrite System 2025 VLDB 6.6235293e-05
4,968 Budget-aware Index Tuning with Reinforcement Learning 2022 SIGMOD 6.3348803e-05
5,430 Materialized View and Index Selection Tool for Microsoft SQL Server 2000 2001 SIGMOD 6.1331043e-05
5,630 ISUM: Efficiently Compressing Large and Complex Workloads for Scalable Index Tuning 2022 SIGMOD 6.0582762e-05
6,105 Breaking It Down: An In-depth Study of Index Advisors 2024 VLDB 5.8860941e-05
6,586 Can Large Language Models Be Query Optimizer for Relational Databases? 2026 SIGMOD 5.7430662e-05
7,072 Plan Stitch: Harnessing the Best of Many Plans 2018 VLDB 5.6074688e-05
7,385 Towards Foundation Database Models 2025 CIDR 5.5385053e-05
7,764 DBG-PT: A Large Language Model Assisted Query Performance Regression Debugger 2024 VLDB 5.4564979e-05
7,900 DISTILL: Low-Overhead Data-Driven Techniques for Filtering and Costing Indexes for Scalable Index Tuning 2022 VLDB 5.4303143e-05
8,771 Automatic Indexing in Oracle 2025 VLDB 5.2806451e-05
9,790 Wii: Dynamic Budget Reallocation In Index Tuning 2024 SIGMOD 5.1260323e-05
10,297 Wred: Workload Reduction for Scalable Index Tuning 2024 SIGMOD 5.0430432e-05
10,359 Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More! 2026 CIDR 4.9793485e-05
10,604 Understanding and Detecting Query Performance Regression in Practical Index Tuning: [Experiments & Analysis] 2026 SIGMOD 4.9793485e-05
11,224 Esc: An Early-Stopping Checker for Budget-aware Index Tuning 2025 VLDB 4.9793485e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 1,516 Automatically Indexing Millions of Databases in Microsoft Azure SQL Database 2019 SIGMOD
2 6,586 Can Large Language Models Be Query Optimizer for Relational Databases? 2026 SIGMOD
3 174 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 2024 VLDB
4 151 An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server 1997 VLDB
5 1,279 AI Meets AI: Leveraging Query Executions to Improve Index Recommendations 2019 SIGMOD
6 10,290 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
7 10,604 Understanding and Detecting Query Performance Regression in Practical Index Tuning: [Experiments & Analysis] 2026 SIGMOD
8 4,711 Learned Index Benefits: Machine Learning Based Index Performance Estimation 2022 VLDB
9 10,971 Verified LLM-Based Query Rewriting for Microsoft SQL Server 2026 VLDB
10 10,359 Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More! 2026 CIDR