We present RubikSQL, a novel NL2SQL system designed to address key challenges in real-world enterprise-level NL2SQL, such as implicit intents and domain-specific terminology. RubikSQL frames NL2SQL as a lifelong learning task, demanding both Knowledge Base (KB) maintenance and SQL generation. RubikSQL systematically builds and refines its KB through techniques including database profiling, structured information extraction, agentic rule mining, and Chain-of-Thought (CoT)-enhanced SQL profiling. RubikSQL then employs a multi-agent workflow to leverage this curated KB, generating accurate SQLs. RubikSQL achieves SOTA performance on both the KaggleDBQA and BIRD Mini-Dev datasets. Finally, we release the RubikBench benchmark, a new benchmark specifically designed to capture vital traits of industrial NL2SQL scenarios, providing a valuable resource for future research.
@article{arxiv.2508.17590,
title = {RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System},
author = {Zui Chen and Han Li and Xinhao Zhang and Xiaoyu Chen and Chunyin Dong and Yifeng Wang and Xin Cai and Su Zhang and Ziqi Li and Chi Ding and Jinxu Li and Shuai Wang and Dousheng Zhao and Sanhai Gao and Guangyi Liu},
journal= {arXiv preprint arXiv:2508.17590},
year = {2025}
}
Comments
18 pages, 3 figures, 3 tables, to be submitted to VLDB 2026 (PVLDB Volume 19)