mlsanityData to 14 Oct 2026

LLM/Agent-as-Data-Analyst: A Survey

arXiv 2509.23988 ↗First posted 28 Sep 2025cs.AI cs.DBcited by 16

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

Abstract (arXiv)

Large language models (LLMs) and agent techniques have brought a fundamental shift in the functionality and development paradigm of data analysis tasks (a.k.a LLM/Agent-as-Data-Analyst), demonstrating substantial impact across both academia and industry. In comparison with traditional rule or small-model based approaches, (agentic) LLMs enable complex data understanding, natural language interfaces, semantic analysis functions, and autonomous pipeline orchestration. From a modality perspective, we review LLM-based techniques for (i) structured data (e.g., NL2SQL, NL2GQL, ModelQA), (ii) semi-structured data (e.g., markup languages understanding, semi-structured table question answering), (iii) unstructured data (e.g., chart understanding, text/image document understanding), and (iv) heterogeneous data (e.g., data retrieval and modality alignment in data lakes). The technical evolution further distills four key design goals for intelligent data analysis agents, namely semantic-aware design, autonomous pipelines, tool-augmented workflows, and support for open-world tasks. Finally, we outline the remaining challenges and propose several insights and practical directions for advancing LLM/Agent-powered data analysis.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 174 of its 274 references that are in the map. First posted on arXiv 28 Sep 2025.

Builds on

174 of 274 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025ALAS: Autonomous Learning Agent for Self-Updating Language Models14 Aug
  2. 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search31 Jan
  3. 2024Multi-Modal Data Exploration via Language Agents24 Dec
  4. 2024NAT-NL2GQL: A Novel Multi-Agent Framework for Translating Natural Language to Graph Query Language11 Dec

Other references · 170

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  8. 2017Inductive Representation Learning on Large Graphscited by 6,320
  9. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  11. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  12. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
38 more
  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  4. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2023Teaching Large Language Models to Self-Debugcited by 988
  7. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  10. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generatorscited by 670
  11. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  12. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  13. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  14. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  15. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
  16. 2022SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animationcited by 382
  17. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 367
  18. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 349
  19. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  20. 2018DVQA: Understanding Data Visualizations via Question Answeringcited by 340
  21. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 256
  22. 2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Datacited by 234
  23. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  24. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  25. 2023Video Understanding with Large Language Models: A Surveycited by 206
  26. 2024Corrective Retrieval Augmented Generationcited by 197
  27. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  28. 2025Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learningcited by 180
  29. 2021FeTaQA: Free-form Table Question Answeringcited by 175
  30. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
  31. 2023ChartLlama: A Multimodal LLM for Chart Understanding and Generationcited by 163
  32. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 160
  33. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 144
  34. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 143
  35. 2023DisCo: Disentangled Control for Realistic Human Dance Generationcited by 142
  36. 2023SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3Dcited by 134
  37. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 129
  38. 2024ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generationcited by 129

50 most cited of 170 All 170 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 12.

16 papers.

Sort:

By area:

  1. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  2. 2025A Survey of AI Scientistscited by 11
  3. 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understandingcited by 7
  4. 2026EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Managementcited by 2
  5. 2025Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisionscited by 1
  6. 2026UPA: Unsupervised Prompt Agent via Tree-Based Search and Selectioncited by 1
  7. 2026Analytical Searchcited by 1
  8. 2026Emerging from Ground: Addressing Intent Deviation in Tool-Using Agents via Deriving Real Calls into Virtual Trajectoriescited by 0
  9. 2026Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directionscited by 0
  10. 2026ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answeringcited by 0
  11. 2026Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoningcited by 0
  12. 2026Compressing Sequences in the Latent Embedding Space: K-Token Merging for Large Language Modelscited by 0
4 more
  1. 2026SemJoin: Semantic Join Optimizationcited by 0
  2. 2026Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation taskscited by 0
  3. 2026Open Tabular Insight Extraction: Where Do We Stand, and Where Should We Go?cited by 0
  4. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey on Large Language Model-based Agents for Statistics and Data Science
  2. 2025Large Language Model-based Data Science Agent: A Survey
  3. 2025LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions
  4. 2025IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis
  5. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
  6. 2024Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis
  7. 2025Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle
  8. 2025LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment