Automating Database-Native Function Code Synthesis with LLMs
Summary: DBCooker targets database-native function synthesis, handling multi-unit registration, source placement, dependencies, and database-specific semantics beyond generic code generation. Plan-guided hybrid filling, progressive validation, and adaptive orchestration improve accuracy 34.55% across SQLite, PostgreSQL, and DuckDB. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Wei Zhou (Shanghai Jiao Tong University)
- 2. Xuanhe Zhou (Shanghai Jiao Tong University)
- 3. Qikang He (Shanghai Jiao Tong University)
- 4. Guoliang Li (Tsinghua University)
- 5. Bingsheng He (National University of Singapore)
- 6. Quanqing Xu (Ant Financial)
- 7. Fan Wu (Shanghai Jiao Tong University)
BibTeX Citation
@inproceedings{zhou_sigmod26,
title = {{Automating Database-Native Function Code Synthesis with LLMs}},
author = {Zhou, Wei and Zhou, Xuanhe and He, Qikang and Li, Guoliang and He, Bingsheng and Xu, Quanqing and Wu, Fan},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802018},
url = {https://dl.acm.org/doi/10.1145/3802018},
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 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 23 | Efficiently Compiling Efficient Query Plans for Modern Hardware | 2011 | VLDB | 0.00054886415 |
| 894 | Froid: Optimization of Imperative Programs in a Relational Database | 2018 | VLDB | 0.00013367658 |
| 1,229 | Weld: A Common Runtime for High Performance Data Analytics | 2017 | CIDR | 0.00011578425 |
| 1,768 | Tuplex: Data Science in Python at Native Code Speed | 2021 | SIGMOD | 9.8041636e-05 |
| 6,327 | Breaking It Down: An In-depth Study of Index Advisors | 2024 | VLDB | 5.9124005e-05 |
| 8,423 | Cracking SQL Barriers: An LLM-based Dialect Translation System | 2025 | SIGMOD | 5.4275169e-05 |
| 10,532 | DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs | 2026 | VLDB | 5.093636e-05 |
| 10,696 | OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML | 2025 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next