mlsanityData to 7 Oct 2026

Data Interpreter: An LLM Agent For Data Science

arXiv 2402.18679 ↗First posted 28 Feb 2024cs.AI cs.LGcited by 222

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

Abstract (arXiv)

Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based agent designed to automatically solve various data science problems end-to-end. Our Data Interpreter incorporates two key modules: 1) Hierarchical Graph Modeling, which breaks down complex problems into manageable subproblems, enabling dynamic node generation and graph optimization; and 2) Programmable Node Generation, a technique that refines and verifies each subproblem to iteratively improve code generation results and robustness. Extensive experiments consistently demonstrate the superiority of Data Interpreter. On InfiAgent-DABench, it achieves a 25% performance boost, raising accuracy from 75.9% to 94.9%. For machine learning and open-ended tasks, it improves performance from 88% to 95%, and from 60% to 97%, respectively. Moreover, on the MATH dataset, Data Interpreter achieves remarkable performance with a 26% improvement compared to state-of-the-art baselines. The code is available at https://github.com/geekan/MetaGPT.

Key facts. Cited by 222 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 59 of its 98 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

59 of 98 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning27 Feb
  2. 2023TaskWeaver: A Code-First Agent Framework29 Nov

Other references · 57

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  8. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  10. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  11. 2024Mixtral of Expertscited by 1,785
  12. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
38 more
  1. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  2. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  4. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  5. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  6. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  9. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  10. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  11. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  12. 2024Understanding the planning of LLM agents: A surveycited by 414
  13. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  14. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  15. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  16. 2023Large Language Models as Tool Makerscited by 293
  17. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  18. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  19. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  20. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  21. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  22. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  23. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  24. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  25. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  26. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
  27. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 98
  28. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 97
  29. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 97
  30. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  31. 2023CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Modelscited by 90
  32. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 85
  33. 2024Language Agents as Optimizable Graphscited by 81
  34. 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
  35. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  36. 2023MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Taskscited by 66
  37. 2024Large Language Model Agent for Hyper-Parameter Optimizationcited by 62
  38. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 36; 2025: 91; 2026: 95.

222 papers.

Sort:

By area:

  1. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  2. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  3. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  4. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  5. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  6. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  7. 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 111
  8. 2024ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulationcited by 106
  9. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
  10. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  11. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLcited by 84
  12. 2024BLADE: Benchmarking Language Model Agents for Data-Driven Sciencecited by 72
38 more
  1. 2024When Search Engine Services meet Large Language Models: Visions and Challengescited by 59
  2. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  3. 2025DataSciBench: An LLM Agent Benchmark for Data Sciencecited by 53
  4. 2024SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositoriescited by 52
  5. 2025MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinementcited by 52
  6. 2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 50
  7. 2026Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Frameworkcited by 50
  8. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  9. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 49
  10. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  11. 2024Adaptive In-conversation Team Building for Language Model Agentscited by 38
  12. 2025MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineeringcited by 38
  13. 2025Self-Supervised Prompt Optimizationcited by 37
  14. 2024Teola: Towards End-to-End Optimization of LLM-based Applicationscited by 32
  15. 2025Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agentscited by 31
  16. 2024LAMBDA: A Large Model Based Data Agentcited by 30
  17. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  18. 2024MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devicescited by 29
  19. 2024Exploring Large Language Models for Feature Selection: A Data-centric Perspectivecited by 27
  20. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaborationcited by 26
  21. 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 26
  22. 2024PyBench: Evaluating LLM Agent on various real-world coding taskscited by 24
  23. 2024Multi-Agent Large Language Models for Conversational Task-Solvingcited by 24
  24. 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflowscited by 23
  25. 2024Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performancecited by 22
  26. 2024A Survey on Large Language Model-based Agents for Statistics and Data Sciencecited by 22
  27. 2025MLZero: A Multi-Agent System for End-to-end Machine Learning Automationcited by 22
  28. 2025Large Language Model-based Data Science Agent: A Surveycited by 22
  29. 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoningcited by 22
  30. 2025Benchmarking Visual Language Models on Standardized Visualization Literacy Testscited by 20
  31. 2025Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executorscited by 20
  32. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Sciencecited by 20
  33. 2024Eliciting the Priors of Large Language Models using Iterated In-Context Learningcited by 19
  34. 2024Transforming Wearable Data into Personal Health Insights using Large Language Model Agentscited by 19
  35. 2024Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Surveycited by 19
  36. 2025RobustFlow: Towards Robust Agentic Workflow Generationcited by 19
  37. 2024Very Large-Scale Multi-Agent Simulation in AgentScopecited by 18
  38. 2025MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answeringcited by 15

50 most cited of 222 All 222 (JSON)

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. 2024DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
  3. 2025DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation
  4. 2026DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation
  5. 2026AgenticDataBench: A Comprehensive Benchmark for Data Agents
  6. 2025Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents
  7. 2025LLM/Agent-as-Data-Analyst: A Survey
  8. 2025IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis