mlsanityData to 7 Oct 2026

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

arXiv 2510.23587 ↗First posted 27 Oct 2025cs.DB cs.AIcited by 30

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

Abstract (arXiv)

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning proactive, generative data agents.

Key facts. Cited by 30 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 147 of its 210 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

147 of 210 references.

Closest ancestors · 16

Same direction, newest first

  1. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Science19 Oct
  2. 2025LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions5 Oct
  3. 2025LLM/Agent-as-Data-Analyst: A Survey28 Sep
  4. 2025Autonomous Data Agents: A New Opportunity for Smart Data23 Sep
  5. 2025AgenticData: An Agentic Data Analytics System for Heterogeneous Data7 Aug
  6. 2025Large Language Model-based Data Science Agent: A Survey2 Aug
  7. 2025Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems2 Jul
  8. 2025QUITE: A Query Rewrite System Beyond Rules with LLM Agents9 Jun
  9. 2025Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets9 Mar
  10. 2024A Survey on Large Language Model-based Agents for Statistics and Data Science18 Dec
  11. 2024AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework10 Dec
  12. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models20 Jun
4 more
  1. 2024CleanAgent: Automating Data Standardization with LLM-based Agents13 Mar
  2. 2024Data Interpreter: An LLM Agent For Data Science28 Feb
  3. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL18 Dec
  4. 2023Agent-OM: Leveraging LLM Agents for Ontology Matching1 Dec

Other references · 131

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  4. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  5. 2023Active Retrieval Augmented Generationcited by 506
  6. 2024Large Language Models: A Surveycited by 506
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2023Cognitive Architectures for Language Agentscited by 422
  9. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  10. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  11. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 377
  12. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
38 more
  1. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  2. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  3. 2022Binding Language Models in Symbolic Languagescited by 224
  4. 2024Large Language Models for Data Annotation and Synthesis: A Surveycited by 201
  5. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  6. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  7. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  8. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  9. 2022Can Foundation Models Wrangle Your Data?cited by 173
  10. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  11. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
  12. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  13. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  14. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  15. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  16. 2025A Comprehensive Survey on Long Context Language Modelingcited by 113
  17. 2024Unifying Multimodal Retrieval via Document Screenshot Embeddingcited by 107
  18. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 98
  19. 2024CRAG -- Comprehensive RAG Benchmarkcited by 94
  20. 2024The Dawn of Natural Language to SQL: Are We Fully Ready?cited by 78
  21. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  22. 2025MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understandingcited by 66
  23. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  24. 2021Towards Natural Language Interfaces for Data Visualization: A Surveycited by 58
  25. 2023Chat2VIS: Generating Data Visualisations via Natural Language using ChatGPT, Codex and GPT-3 Large Language Modelscited by 58
  26. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  27. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  28. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  29. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  30. 2024VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generationcited by 40
  31. 2024Data-driven Discovery with Large Generative Modelscited by 33
  32. 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 33
  33. 2024Match, Compare, or Select? An Investigation of Large Language Models for Entity Matchingcited by 32
  34. 2025Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoningcited by 32
  35. 2023Entity Matching using Large Language Modelscited by 31
  36. 2025NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translationcited by 31
  37. 2025Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scalingcited by 30
  38. 2023PDFTriage: Question Answering over Long, Structured Documentscited by 29

50 most cited of 131 All 131 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 30.

30 papers.

Sort:

By area:

  1. 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestrationcited by 30
  2. 2026AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machinescited by 20
  3. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  4. 2026Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMscited by 9
  5. 2026InfoPO: Information-Driven Policy Optimization for User-Centric Agentscited by 8
  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. 2026Text2GraphQuery-Bench: A Text to Graph Query Benchmarkcited by 3
  9. 2026Automatic End-to-End Data Integration using Large Language Modelscited by 3
  10. 2026PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?cited by 3
  11. 2026PeroMAS: A Multi-agent System of Perovskite Material Discoverycited by 2
  12. 2026CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programmingcited by 2
18 more
  1. 2026EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Managementcited by 2
  2. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2
  3. 2026DataMagic: Transforming Tabular Data into Data Insight Videocited by 2
  4. 2026Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuelcited by 1
  5. 2026SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognitioncited by 1
  6. 2026Scalable Environments Drive Generalizable Agentscited by 1
  7. 2026Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systemscited by 1
  8. 2026SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestrationcited by 1
  9. 2026MaDI-Bench: An End-to-End Data Integration Benchmarkcited by 1
  10. 2026FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skillscited by 1
  11. 2026stratum: A System Infrastructure for Massive Agent-Centric ML Workloadscited by 0
  12. 2026Dial: A Knowledge-Grounded Dialect-Specific NL2SQL Systemcited by 0
  13. 2026Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systemscited by 0
  14. 2026ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Modelscited by 0
  15. 2026AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysiscited by 0
  16. 2026Data Agents: Agentic Data Systemscited by 0
  17. 2026Fail Loudly: An Auditable Runtime for Agentic Data Analysiscited by 0
  18. 2026DataVista: Diagnosing Multimodal LLMs on Data Video Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
  2. 2025Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
  3. 2026Exploring Autonomous Agentic Data Engineering for Model Specialization
  4. 2026DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
  5. 2025What's the next frontier for Data-centric AI? Data Savvy Agents
  6. 2025Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents
  7. 2026AgenticDataBench: A Comprehensive Benchmark for Data Agents
  8. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses