mlsanityData to 14 Oct 2026

Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence

arXiv 2507.10281 ↗First posted 14 Jul 2025cs.AI cs.DBcited by 2

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

Abstract (arXiv)

Tables are fundamental in domains such as finance, healthcare, and public administration, yet real-world table tasks often involve noise, structural heterogeneity, and semantic complexity--issues underexplored in existing research that primarily targets clean academic datasets. This survey focuses on LLM-based Table Agents, which aim to automate table-centric workflows by integrating preprocessing, reasoning, and domain adaptation. We define five core competencies--C1: Table Structure Understanding, C2: Table and Query Semantic Understanding, C3: Table Retrieval and Compression, C4: Executable Reasoning with Traceability, and C5: Cross-Domain Generalization--to analyze and compare current approaches. In addition, a detailed examination of the Text-to-SQL Agent reveals a performance gap between academic benchmarks and real-world scenarios, especially for open-source models. Finally, we provide actionable insights to improve the robustness, generalization, and efficiency of LLM-based Table Agents in practical settings.

Key facts. Cited by 2 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 119 of its 186 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

119 of 186 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents10 Nov
  2. 2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL15 Aug
  3. 2024SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration19 Jun
  4. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks10 Jan

Other references · 115

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  7. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  8. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  9. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 733
  10. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  11. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  12. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
38 more
  1. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  2. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  3. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  4. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  5. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  6. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
  7. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  8. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  9. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
  10. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  11. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  12. 2023Certifying LLM Safety against Adversarial Promptingcited by 266
  13. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  14. 2023Challenges and Applications of Large Language Modelscited by 254
  15. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  16. 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 196
  17. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  18. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 185
  19. 2021FeTaQA: Free-form Table Question Answeringcited by 175
  20. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  21. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  22. 2025Qwen2.5-1M Technical Reportcited by 164
  23. 2021Monte Carlo Tree Search: A Review of Recent Modifications and Applicationscited by 161
  24. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  25. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
  26. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  27. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 121
  28. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 118
  29. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  30. 2024Efficient Adversarial Training in LLMs with Continuous Attackscited by 113
  31. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  32. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  33. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 88
  34. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 78
  35. 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
  36. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  37. 2019Sherlock: A Deep Learning Approach to Semantic Data Type Detectioncited by 74
  38. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72

50 most cited of 115 All 115 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoningcited by 10
  2. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2025Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration
  2. 2025LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions
  3. 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion
  4. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
  5. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  6. 2025Large Language Model-based Data Science Agent: A Survey
  7. 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
  8. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation