DBScholar

Back to papers

SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation

Summary: SQL-Factory: a modular multi-agent pipeline splitting SQL synthesis into Generation (diverse structures via a strong LLM), Expansion (cheap scaling via a lightweight LLM), and Management (adaptive scheduling and quality control). Generates >300k diverse SQLs for <$200 API cost and boosts downstream Text-to-SQL performance. (summarized by gpt-5-mini on Mar 13 2026)

Paper ID
hd5f1125473a8cd58
Venue
VLDB
Year
2026
Pagerank
5.2056825e-05
Overall Rank
9,222 | 38.00%
DOI
10.14778/3778092.3778093

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{li_vldb26,
        title = {{SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation}},
        author = {Li, Jiahui and Wu, Tongwang and Mao, Yuren and Gao, Yunjun and Feng, Yajie and Liu, Huaizhong},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {3},
        pages = {292--305},
        doi = {10.14778/3778092.3778093},
        url = {https://doi.org/10.14778/3778092.3778093},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
10,714 SQL-Exchange: Transforming SQL Queries Across Domains 2026 VLDB 4.9793485e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 19 of 19 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
78 Automatic Database Management System Tuning Through Large-scale Machine Learning 2017 SIGMOD 0.00036684414
174 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 2024 VLDB 0.00026790979
314 An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning 2019 SIGMOD 0.00021282642
383 Massive Stochastic Testing of SQL 1998 VLDB 0.00019484034
479 The Making of TPC-DS 2006 VLDB 0.00017622471
533 CodeS: Towards Building Open-source Language Models for Text-to-SQL 2024 SIGMOD 0.00016826571
1,515 DSB: A Decision Support Benchmark for Workload-Driven and Traditional Database Systems 2021 VLDB 0.00010417728
1,658 D-Bot: Database Diagnosis System using Large Language Models 2024 VLDB 9.9642078e-05
1,777 OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale 2025 VLDB 9.664552e-05
1,866 ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems 2024 VLDB 9.481643e-05
3,327 Robust Query Driven Cardinality Estimation under Changing Workloads 2023 VLDB 7.4207879e-05
4,311 ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads 2024 VLDB 6.6727978e-05
4,331 FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis 2024 SIGMOD 6.6590534e-05
4,482 LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning 2022 SIGMOD 6.5802486e-05
4,707 PreQR: Pre-training Representation for SQL Understanding 2022 SIGMOD 6.4587914e-05
6,660 Speeding Up End-to-end Query Execution via Learning-based Progressive Cardinality Estimation 2023 SIGMOD 5.7178404e-05
8,753 A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach 2025 SIGMOD 5.2846898e-05
9,109 Generation of Training Examples for Tabular Natural Language Inference 2023 SIGMOD 5.2280464e-05
9,620 Db2une: Tuning Under Pressure via Deep Learning 2024 VLDB 5.1501614e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 7,638 Test Data Generation for Complex SQL Queries 2026 SIGMOD
2 10,686 SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL 2026 SIGMOD
3 10,893 Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation 2026 VLDB
4 10,738 OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision 2026 VLDB
5 10,973 Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents 2026 VLDB
6 4,482 LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning 2022 SIGMOD
7 174 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 2024 VLDB
8 10,958 SpatialSQL: A Multi-Agent System for Interactive and Observable Spatial Text-to-SQL 2026 VLDB
9 6,220 GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise 2025 CIDR
10 2,025 OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment 2025 SIGMOD