RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System

arXiv 2508.17590 ↗First posted 25 Aug 2025cs.DB cs.AI cs.CLcited by 4

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 48 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

27 of 48 references.

Closest ancestors · 1

Same direction, newest first

2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL18 Dec

Other references · 26

2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
2022Large Language Models are Zero-Shot Reasonerscited by 4,374
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 148

14 more

2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 106
2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 105
2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
2021Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Datacited by 43
2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 42
2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 34
2025Automatic Metadata Extraction for Text-to-SQLcited by 27
2023Selective Demonstrations for Cross-domain Text-to-SQLcited by 21
2025AI-native Memory 2.0: Second Mecited by 14
2024BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domaincited by 10
2025Knowledge Base Construction for Knowledge-Augmented Text-to-SQLcited by 9
2024BIS: NL2SQL Service Evaluation Benchmark for Business Intelligence Scenarioscited by 3
2025TailorSQL: An NL2SQL System Tailored to Your Query Workloadcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

Similar, not cited

Close in wording, no citation either way