Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents
Summary: GenDB uses LLM agents to generate instance-, workload-, and hardware-optimized query-execution code, shifting engine development toward generative programming. Its hybrid design targets repetitive templates, with interactive profiling and fuzz/inspection validation, while exposing generation cost and correctness limitations. (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. Jiale Lao (Cornell University)
- 2. Immanuel Trummer (Cornell University)
BibTeX Citation
@article{lao_vldb26,
title = {{Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents}},
author = {Lao, Jiale and Trummer, Immanuel},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4602--4605},
doi = {10.14778/3827998.3828076},
url = {https://doi.org/10.14778/3827998.3828076},
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 7 of 7 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 |
| 21 | Efficiently Compiling Efficient Query Plans for Modern Hardware | 2011 | VLDB | 0.00056855599 |
| 495 | Building Efficient Query Engines in a High-Level Language | 2014 | VLDB | 0.00017370758 |
| 605 | Everything You Always Wanted to Know About Compiled and Vectorized Queries But Were Afraid to Ask | 2018 | VLDB | 0.00015647561 |
| 1,839 | Why TPC Is Not Enough: An Analysis of the Amazon Redshift Fleet | 2024 | VLDB | 9.5304799e-05 |
| 1,975 | CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions using GPT-3 Codex | 2022 | VLDB | 9.2807031e-05 |
| 7,822 | Bespoke OLAP: Synthesizing Workload-Specific One-size-fits-one Database Engines | 2026 | VLDB | 5.4461624e-05 |
Previous
Page 1 / 1
Next