SLM-Augmented PostgreSQL Query Optimization
-
DOI:
https://doi.org/10.67228/30715628/ICIoTCAA-2026P105Published 08-31-2026
Small Language Models, PostgreSQL, Query Optimization, Database Performance, SQL Query Rewriting, Index Recommendation, Query Planner Optimization, AI-Augmented Databases, Healthcare Database Systems, Safe AI Deployment Issue
Section
ArticlesAbstract
Database performance is one of the few problems that never stays solved. As data grows and access patterns shift, queries that were fast become slow, indexes that were right become wrong, and the tuning work begins again. Traditionally this work is manual, expert-intensive, and reactive. I designed an SLM-augmented query optimization pipeline for our PostgreSQL estate a small language model deployed inside our own network that continuously analyzes query workload and recommends rewrites, indexes, and planner hints. This article describes the design, and more importantly, the safety architecture that makes AI in the database layer responsible rather than reckless in a regulated healthcare environment.
References
[1] Kaoudi, Zoi, and Ioana Giurgiu. "Query Optimization Beyond Data Systems: The Case for Multi-Agent Systems." arXiv preprint arXiv:2512.11001 (2025).
[2] Yan, Zhengtong, et al. "DBMS-LLM Integration Strategies in Industrial and Business Applications: Current Status and Future Challenges." arXiv preprint arXiv:2507.19254 (2025).
[3] Qu, Ge, et al. "SHARE: An SLM-based hierarchical action CorREction assistant for text-to-SQL." Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
[4] Glenn, Parker, Alfy Samuel, and Daben Liu. "Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative ProgrSingh, Sarvjeet, et al. "Query Selectivity Estimation for Uncertain Database." (2007).
[5] Singh, Sarvjeet, et al. "Query Selectivity Estimation for Uncertain Database." (2007).ams." arXiv preprint arXiv:2509.20208 (2025).
[6] Stonebraker, Michael, and Lawrence A. Rowe. "The design of Postgres." ACM Sigmod Record 15.2 (1986): 340-355.
[7] Zhou, Feng, et al. "Nabil: A text-to-SQL model based on brain-inspired computing techniques and large language modeling." Electronics 14.19 (2025): 3910.
[8] Sharma, Anantha, et al. "Mitigating hallucinationZeroG: An advanced knowledge management engine." 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA). IEEE, 2025.
[9] Singh, Sarvjeet, et al. "Query Selectivity Estimation for Uncertain Database." (2007).
[10] Platt, Nolan, and Pragyansmita Nayak. "Multi-Model Synthetic Training for Mission-Critical Small Language Models." 2025 3rd International Conference on Foundation and Large Language Models (FLLM). IEEE, 2025.
[11] Sun, Wenbo, et al. "TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware." Proceedings of the ACM on Management of Data 3.6 (2025): 1-27.
[12] Quoc Anh, Nguyen, et al. "Small Language Models For Efficient Domain Data Retrieval Using Structured Query Language from Natural Language." Nguyen and Gia Hy, Truong and Ha, Son, Small Language Models For Efficient Domain Data Retrieval Using Structured Query Language from Natural Language (December 09, 2025) (2025).
[13] Shah, Sarvjeet Singh Chris Mayfield Rahul, and Sunil Prabhakar Susanne Hambrusch. "Query Selectivity Estimation for Uncertain Data." (2007).
[14] Wang, Jing, et al. "Revisiting secondary indexing in {LSM-based} storage systems with persistent memory." 2023 USENIX Annual Technical Conference (USENIX ATC 23). 2023.
[15] Caldeira, Carlos Eduardo, et al. "LLM-Based Text-to-SQL for SparkSQL Queries in Manufacturing Data Lakes: An Architecture for Industry 4.0." 2025 12th International Conference on Soft Computing & Machine Intelligence (ISCMI). IEEE, 2025.
[16] Wang, Jing, et al. "Perseid: A secondary indexing mechanism for LSM-based storage systems." ACM Transactions on Storage 20.2 (2024): 1-28.
Downloads
Similar Articles
- Dr. Lucas Martin, Dr. Chloe Bernard, Innovations in Smart Retail Using Real-Time Analytics , International Journal of Modern Innovations and Emerging Trends: Vol. 3 No. 2 (2020)
- Madhurima Kommuru, IDE Agent Mode Explained: When to Use It and Which Model to Pick , International Journal of Modern Innovations and Emerging Trends: Vol. 8 No. 2 (2025)
- Dr. Meena Krishnan, The Emergence of Explainable Artificial Intelligence in Modern Decision Systems , International Journal of Modern Innovations and Emerging Trends: Vol. 6 No. 1 (2023)
- Jacques Arsac, Intelligent Transportation Systems Using Vehicle-to-Everything (V2X) Communication , International Journal of Modern Innovations and Emerging Trends: Vol. 7 No. 2 (2024)
- Dr. Rajesh Kumar Sharma, AI-Driven Customer Behavior Analysis in E-Commerce Platforms , International Journal of Modern Innovations and Emerging Trends: Vol. 1 No. 2 (2018)
- Rama Subba Rao Nimmala, The Art of System Debugging: Root Cause Analysis for Hardware and Software Engineers , International Journal of Modern Innovations and Emerging Trends: Vol. 7 No. 1 (2024)
- Bapu Rao Srigadde, How to Avoid Recursive Triggers , International Journal of Modern Innovations and Emerging Trends: ICIoTCAA26 - Conference Proceeding
- Narendra Karmarkar, P. K. Iyengar, Agentic AI Architectures for Autonomous Business Applications , International Journal of Modern Innovations and Emerging Trends: Vol. 7 No. 1 (2024)
- Per Brinch Hansen, Borge Diderichsen, Synthetic Data Generation Models for Privacy-Safe AI , International Journal of Modern Innovations and Emerging Trends: Vol. 7 No. 2 (2024)
- Vijaya Ragavan, Neela Rohit, Salim Nazar Mohammed, Neural Network Models for High-Precision Predictive Maintenance , International Journal of Modern Innovations and Emerging Trends: Vol. 9 No. 1 (2026)
You may also start an advanced similarity search for this article.