Andromeda: Debugging Database Performance Issues with Retrieval-Augmented Large Language Models
Summary: Andromeda uses retrieval-augmented LLMs to debug DBMS performance with context-aware guidance. Evidence from historical queries, manuals, telemetry, and execution logs is retrieved to adapt an open-source LLM for domain-specific debugging, shown via a web app. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Pengyi Wang (Renmin University of China)
- 2. Sibei Chen (Renmin University of China)
- 3. Ju Fan (Renmin University of China)
- 4. Bin Wu (Alibaba)
- 5. Nan Tang (Hong Kong University of Science and Technology)
- 6. Jian Tan (Alibaba)
BibTeX Citation
@inproceedings{wang_sigmod25,
title = {{Andromeda: Debugging Database Performance Issues with Retrieval-Augmented Large Language Models}},
author = {Wang, Pengyi and Chen, Sibei and Fan, Ju and Wu, Bin and Tang, Nan and Tan, Jian},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3725080},
url = {https://dl.acm.org/doi/10.1145/3722212.3725080},
year = {2025}
}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 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,337 | DB-BERT: A Database Tuning Tool that "Reads the Manual" | 2022 | SIGMOD | 0.00011117488 |
| 1,920 | D-Bot: Database Diagnosis System using Large Language Models | 2024 | VLDB | 9.4846185e-05 |
| 3,757 | Panda: Performance Debugging for Databases using LLM Agents | 2024 | CIDR | 7.1483644e-05 |
| 5,856 | Automatic Database Configuration Debugging using Retrieval-Augmented Language Models | 2025 | SIGMOD | 6.0644656e-05 |
Previous
Page 1 / 1
Next