EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SQLMind: A Large-Model–Driven Adaptive Query Optimization Framework for Cloud Databases

Yi Yang, Ziyi Ye, Kaijie Zhang

Fundamental Scientific Reports in Multidisciplinary Areas · 25.05.2026 · 2 (02) · 278-288

DOI: 10.66238/fsrma81 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fundamental Scientific Reports in Multidisciplinary Areas, online erschienen am 25.05.2026. Verfasst von Yi Yang und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud database systems increasingly operate under highly dynamic workloads, heterogeneous data distributions, and rapidly evolving application requirements, which place substantial demands on the robustness and adaptability of query optimizers. Traditional rule-based or cost-model—driven optimizers often struggle to generalize across diverse execution environments, leading to suboptimal query plans and inefficient resource utilization. To address these challenges, this paper proposes SQLMind, a large-model—driven adaptive query optimization framework designed specifically for cloud database settings. SQLMind integrates four tightly coupled components: (1) a Large Language Model-based SQL Semantic Interpreter that understands complex SQL intent and contextual constraints, (2) a Query Rewriter that generates semantically equivalent but performance-enhanced SQL variants, (3) an Index and Candidate Plan Generator that synthesizes structural optimization opportunities, and (4) a Reinforcement-Learning-based Plan Selector that continuously improves execution-plan decisions based on real runtime feedback. This unified architecture enables SQLMind to combine natural-language reasoning, structural SQL transformation, and data-driven plan optimization, forming a self-evolving query optimization pipeline. Experiments conducted on a cloud-native workload dataset demonstrate that SQLMind delivers substantial performance gains over both PostgreSQL’s default optimizer and strong learning-based baselines. The framework achieves a 38.6% reduction in query latency, 84.1% plan-selection accuracy, and a 27.3% improvement in throughput, while maintaining a near-zero invalid rewrite rate. These results confirm that combining large-model semantic reasoning with reinforcement-learning-based plan optimization yields consistently superior adaptive query performance in cloud database environments.

Zitieren

APA

Yang, Y., Ye, Z., & Zhang, K. (2026). SQLMind: A Large-Model–Driven Adaptive Query Optimization Framework for Cloud Databases. Fundamental Scientific Reports in Multidisciplinary Areas, 2(02), 278-288. https://doi.org/10.66238/fsrma81

Vancouver

Yang Y, Ye Z, Zhang K. SQLMind: A Large-Model–Driven Adaptive Query Optimization Framework for Cloud Databases. Fundamental Scientific Reports in Multidisciplinary Areas. 2026;2(02):278-288. doi:10.66238/fsrma81

BibTeX
@article{Yang2026,
  author = {Yang, Yi and Ye, Ziyi and Zhang, Kaijie},
  title = {SQLMind: A Large-Model–Driven Adaptive Query Optimization Framework for Cloud Databases},
  journal = {Fundamental Scientific Reports in Multidisciplinary Areas},
  year = {2026},
  volume = {2},
  number = {02},
  pages = {278--288},
  doi = {10.66238/fsrma81}
}
Kostenlos starten →