RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915461102305280 |
|---|---|
| author | Chen, Zui Li, Han Zhang, Xinhao Chen, Xiaoyu Dong, Chunyin Wang, Yifeng Cai, Xin Zhang, Su Li, Ziqi Ding, Chi Li, Jinxu Wang, Shuai Zhao, Dousheng Gao, Sanhai Liu, Guangyi |
| author_facet | Chen, Zui Li, Han Zhang, Xinhao Chen, Xiaoyu Dong, Chunyin Wang, Yifeng Cai, Xin Zhang, Su Li, Ziqi Ding, Chi Li, Jinxu Wang, Shuai Zhao, Dousheng Gao, Sanhai Liu, Guangyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17590 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System Chen, Zui Li, Han Zhang, Xinhao Chen, Xiaoyu Dong, Chunyin Wang, Yifeng Cai, Xin Zhang, Su Li, Ziqi Ding, Chi Li, Jinxu Wang, Shuai Zhao, Dousheng Gao, Sanhai Liu, Guangyi Databases Artificial Intelligence Computation and Language Multiagent Systems H.2.3; I.2.4; I.2.7 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. |
| title | RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System |
| topic | Databases Artificial Intelligence Computation and Language Multiagent Systems H.2.3; I.2.4; I.2.7 |
| url | https://arxiv.org/abs/2508.17590 |