ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling
Summary: ReSequel adds an LLM-driven outer optimization layer that uses metadata-derived query templates, sampled-data verification, and performance ranking to safely explore rewrites. Across eight benchmarks and three DBMSs, it achieves up to 16× workload speedups over native optimizers. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Saeed Fathollahzadeh (Concordia University)
- 2. Essam Mansour (Concordia University)
- 3. Matthias Boehm (Berlin Institute for the Foundations of Learning and Data; Technical University of Berlin)
BibTeX Citation
@article{fathollahzadeh_vldb26,
title = {{ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling}},
author = {Fathollahzadeh, Saeed and Mansour, Essam and Boehm, Matthias},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {10},
pages = {2880--2893},
doi = {10.14778/3828612.3828639},
url = {https://doi.org/10.14778/3828612.3828639},
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 4 of 54 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,113 | Presto’s History-based Query Optimizer | 2024 | VLDB | 5.2276066e-05 |
| 10,140 | How to Optimize SQL Queries? A Comparison Between Split, Holistic, and Hybrid Approaches | 2025 | VLDB | 5.0742707e-05 |
| 10,334 | Efficient Enumeration of Recursive Plans in Transformation-based Query Optimizers | 2024 | VLDB | 5.0254535e-05 |
| 10,335 | Zed: Leveraging Data Types to Process Eclectic Data | 2023 | CIDR | 5.0254535e-05 |