Reading List of LLM-based Data Science Agents.

This is the recommended reading list for the paper ”A Survey on Large Language Model-based Agents for Statistics and Data Science“

Data Science Agent

• AUTOMIND: Adaptive Knowledgeable Agent for Automated Data Science (GitHub)
• ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering (Github)
• I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search
• AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
• AutoM3L: An Automated Multimodal Machine Learning Framework with Large Language Models
• AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
• ChatGPT as your Personal Data Scientist
• Data Interpreter: An LLM Agent For Data Science
• Data Formulator 2: Iteratively Creating Rich Visualizations with AI
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
• Execution-based Evaluation for Data Science Code Generation Models
• HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
• InsightPilot: An LLM-Empowered Automated Data Exploration System
• Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis
• Is GPT-4 a Good Data Analyst?
• JarviX: A LLM No-code Platform for Tabular Data Analysis and Optimization
• LAMBDA: A Large Model-Based Data Agent (Github)
• Large Language Models as Data Preprocessors
• Large Language Models for Tabular Data: Progresses and Future Directions
• Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering
• LLM-Enhanced Data Management
• MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
• MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks
• OpenAgents: An Open Platform for Language Agents in the Wild
• SEED: Domain-Specific Data Curation With Large Language Models
• SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
• TaskWeaver: A Code-First Agent Framework
• Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries
• Training and Evaluating a Jupyter Notebook Data Science Assistant
• WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization
• XInsight: eXplainable Data Analysis Through The Lens of Causality

Evaluation-related Works

• Benchmarking Data Science Agents
• BLADE: Benchmarking Language Model Agents for Data-Driven Science
• DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
• DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
• InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
• Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

Survey

• Data Analysis in the Era of Generative AI
• Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents
• Large Language Models for Data Science: A Survey

Welcome to submit additions

---

If you find our work useful in your research, consider citing our paper by:

@article{sun2025survey,
  title={A survey on large language model-based agents for statistics and data science},
  author={Sun, Maojun and Han, Ruijian and Jiang, Binyan and Qi, Houduo and Sun, Defeng and Yuan, Yancheng and Huang, Jian},
  journal={The American Statistician},
  pages={1--14},
  year={2025},
  publisher={Taylor \& Francis}
}

@article{sun2025lambda,
  title={Lambda: A large model based data agent},
  author={Sun, Maojun and Han, Ruijian and Jiang, Binyan and Qi, Houduo and Sun, Defeng and Yuan, Yancheng and Huang, Jian},
  journal={Journal of the American Statistical Association},
  pages={1--13},
  year={2025},
  publisher={Taylor \& Francis}
}