mlsanityData to 7 Oct 2026

Large Language Model-based Data Science Agent: A Survey

arXiv 2508.02744 ↗First posted 2 Aug 2025cs.AIcited by 22

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

Abstract (arXiv)

The rapid advancement of Large Language Models (LLMs) has driven novel applications across diverse domains, with LLM-based agents emerging as a crucial area of exploration. This survey presents a comprehensive analysis of LLM-based agents designed for data science tasks, summarizing insights from recent studies. From the agent perspective, we discuss the key design principles, covering agent roles, execution, knowledge, and reflection methods. From the data science perspective, we identify key processes for LLM-based agents, including data preprocessing, model development, evaluation, visualization, etc. Our work offers two key contributions: (1) a comprehensive review of recent developments in applying LLMbased agents to data science tasks; (2) a dual-perspective framework that connects general agent design principles with the practical workflows in data science.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 82 of its 127 references that are in the map. First posted on arXiv 2 Aug 2025.

Builds on

82 of 127 references.

Closest ancestors · 24

Same direction, newest first

  1. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Science12 Jun
  2. 2025DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation20 May
  3. 2025SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science30 Mar
  4. 2025Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets9 Mar
  5. 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agents20 Feb
  6. 2025DataSciBench: An LLM Agent Benchmark for Data Science19 Feb
  7. 2025ML-Dev-Bench: Comparative Analysis of AI Agents on ML development workflows3 Feb
  8. 2024A Survey on Large Language Model-based Agents for Statistics and Data Science18 Dec
  9. 2024DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models9 Oct
  10. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering9 Oct
  11. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery7 Oct
  12. 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?12 Sep
12 more
  1. 2024SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories11 Sep
  2. 2024BLADE: Benchmarking Language Model Agents for Data-Driven Science19 Aug
  3. 2024LAMBDA: A Large Model Based Data Agent24 Jul
  4. 2024Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?15 Jul
  5. 2024InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation8 Jul
  6. 2024CleanAgent: Automating Data Standardization with LLM-based Agents13 Mar
  7. 2024Data Interpreter: An LLM Agent For Data Science28 Feb
  8. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning27 Feb
  9. 2024Benchmarking Data Science Agents27 Feb
  10. 2024Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis2 Feb
  11. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks10 Jan
  12. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation5 Oct

Other references · 58

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  3. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  4. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  5. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  6. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  7. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  8. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 306
  9. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  10. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
  11. 2024AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environmentscited by 215
  12. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
38 more
  1. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  2. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  3. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 112
  4. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 98
  5. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  6. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLcited by 84
  7. 2023AutoML-GPT: Automatic Machine Learning with GPTcited by 80
  8. 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
  9. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 73
  10. 2024AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitionscited by 70
  11. 2023ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Codecited by 63
  12. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  13. 2024Large Language Model Agent for Hyper-Parameter Optimizationcited by 62
  14. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scalecited by 61
  15. 2023CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulescited by 58
  16. 2024MASAI: Modular Architecture for Software-engineering AI Agentscited by 49
  17. 2024AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodologycited by 45
  18. 2024FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Modelscited by 39
  19. 2023Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queriescited by 38
  20. 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualizationcited by 38
  21. 2024SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agentscited by 34
  22. 2024CodeTree: Agent-guided Tree Search for Code Generation with Large Language Modelscited by 32
  23. 2024CodeS: Natural Language to Code Repository via Multi-Layer Sketchcited by 28
  24. 2024Exploring Large Language Models for Feature Selection: A Data-centric Perspectivecited by 27
  25. 2024DataNarrative: Automated Data-Driven Storytelling with Visualizations and Textscited by 25
  26. 2024PyBench: Evaluating LLM Agent on various real-world coding taskscited by 24
  27. 2024SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learningcited by 23
  28. 2024AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmarkcited by 23
  29. 2023ChatGPT as your Personal Data Scientistcited by 22
  30. 2024An LLM Agent for Automatic Geospatial Data Analysiscited by 21
  31. 2024LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Executioncited by 20
  32. 2024BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Taskscited by 19
  33. 2024MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domainscited by 18
  34. 2025EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Designcited by 18
  35. 2024Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agentscited by 17
  36. 2024From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systemscited by 16
  37. 2025TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agentscited by 14
  38. 2024AutoM3L: An Automated Multimodal Machine Learning Framework with Large Language Modelscited by 13

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 20.

22 papers.

Sort:

By area:

  1. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  2. 2026Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systemscited by 11
  3. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  4. 2026LongDA: Benchmarking LLM Agents for Long-Document Data Analysiscited by 6
  5. 2025AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systemscited by 5
  6. 2026Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysiscited by 4
  7. 2026LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysiscited by 4
  8. 2026Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolutioncited by 4
  9. 2026Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Callingcited by 3
  10. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2
  11. 2026DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrievalcited by 1
  12. 2026Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Lengthcited by 1
10 more
  1. 2026Multi-Agent Coordination Adaptation via Structure-Guided Orchestrationcited by 1
  2. 2026"Skill Issues'': Data-Centric Optimization of Lakehouse Agentscited by 1
  3. 2026MaDI-Bench: An End-to-End Data Integration Benchmarkcited by 1
  4. 2026Autonomous Data Processing using Meta-Agentscited by 0
  5. 2026AutoHealth: An Uncertainty-Aware Multi-Agent System for Autonomous Health Data Modelingcited by 0
  6. 2026Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMscited by 0
  7. 2026Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflowscited by 0
  8. 2026From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systemscited by 0
  9. 2026SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFEcited by 0
  10. 2026Skill-based Agentic Evaluation for Real-time Data Science Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions
  2. 2025LLM/Agent-as-Data-Analyst: A Survey
  3. 2026AgenticDataBench: A Comprehensive Benchmark for Data Agents
  4. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
  5. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  6. 2025Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents
  7. 2025DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation
  8. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects