# Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned

arXiv: https://arxiv.org/abs/2407.21040 · HTML: https://mlsanity.com/paper/2407.21040/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 21 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Natural SQL: Making SQL Easier to Infer from Natural Language Specifications](https://mlsanity.com/paper/2109.05153/) (2021)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [AI-assisted coding: Experiments with GPT-4](https://mlsanity.com/paper/2304.13187/) (2023)
- [Fine-Tuning Language Models for Context-Specific SQL Query Generation](https://mlsanity.com/paper/2312.02251/) (2023)

## Built on by (most cited first, 3 of 3)

- [Large Language Model-based Data Science Agent: A Survey](https://mlsanity.com/paper/2508.02744/) (2025)
- [Pre-trained Graphformer-based Ranking at Web-scale Search (Extended Abstract)](https://mlsanity.com/paper/2409.16590/) (2024)
- [Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)](https://mlsanity.com/paper/2409.16594/) (2024)

## Abstract (arXiv)

While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge. This study introduces SageCopilot, an advanced, industry-grade system system that automates the data science pipeline by integrating Large Language Models (LLMs), Autonomous Agents (AutoAgents), and Language User Interfaces (LUIs). Specifically, SageCopilot incorporates a two-phase design: an online component refining users' inputs into executable scripts through In-Context Learning (ICL) and running the scripts for results reporting & visualization, and an offline preparing demonstrations requested by ICL in the online phase. A list of trending strategies such as Chain-of-Thought and prompt-tuning have been used to augment SageCopilot for enhanced performance. Through rigorous testing and comparative analysis against prompt-based solutions, SageCopilot has been empirically validated to achieve superior end-to-end performance in generating or executing scripts and offering results with visualization, backed by real-world datasets. Our in-depth ablation studies highlight the individual contributions of various components and strategies used by SageCopilot to the end-to-end correctness for data sciences.