mlsanityData to 14 Oct 2026

TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering

arXiv 2509.01312 ↗First posted 1 Sep 2025cs.CLcited by 3

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

Abstract (arXiv)

While large language models (LLMs) have shown promise in the table question answering (TQA) task through prompt engineering, they face challenges in industrial applications, including structural heterogeneity, difficulties in target data localization, and bottlenecks in complex reasoning. To address these limitations, this paper presents TableZoomer, a novel LLM-powered, programming-based agent framework. It introduces three key innovations: (1) replacing the original fully verbalized table with structured table schema to bridge the semantic gap and reduce computational complexity; (2) a query-aware table zooming mechanism that dynamically generates sub-table schema through column selection and entity linking, significantly improving target localization efficiency; and (3) a Program-of-Thoughts (PoT) strategy that transforms queries into executable code to mitigate numerical hallucination. Additionally, we integrate the reasoning workflow with the ReAct paradigm to enable iterative reasoning. Extensive experiments demonstrate that our framework maintains the usability advantages while substantially enhancing performance and scalability across tables of varying scales. When implemented with the Qwen3-8B-Instruct LLM, TableZoomer achieves accuracy improvements of 19.34% and 25% over conventional PoT methods on the large-scale DataBench dataset and the small-scale Fact Checking task of TableBench dataset, respectively.

Key facts. Cited by 3 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 48 of its 71 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

48 of 71 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL18 Dec

Other references · 47

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2025Qwen3 Technical Reportcited by 8,820
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  9. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  10. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  11. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  12. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 239
35 more
  1. 2022Binding Language Models in Symbolic Languagescited by 228
  2. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  3. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 178
  4. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
  5. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 128
  6. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 77
  7. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  8. 2024AI Flow at the Network Edgecited by 46
  9. 2025AI Flow: Perspectives, Scenarios, and Approachescited by 44
  10. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  11. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 41
  12. 2022Positive-incentive Noisecited by 39
  13. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  14. 2023Variational Positive-incentive Noise: How Noise Benefits Modelscited by 38
  15. 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 37
  16. 2024Enhance Vision-Language Alignment with Noisecited by 34
  17. 2024Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extractioncited by 33
  18. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  19. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  20. 2020LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Networkcited by 26
  21. 2013Learning to Rank for Blind Image Quality Assessmentcited by 25
  22. 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasonerscited by 25
  23. 2024Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noisecited by 25
  24. 2024Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Datacited by 24
  25. 2024Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolutioncited by 19
  26. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  27. 2024Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Mergingcited by 16
  28. 2024TeleChat Technical Reportcited by 15
  29. 2025Learn Beneficial Noise as Graph Augmentationcited by 15
  30. 2024PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tablescited by 14
  31. 2024Tele-FLM Technical Reportcited by 12
  32. 2024You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQLcited by 11
  33. 2025Technical Report of TeleChat2, TeleChat2.5 and T1cited by 10
  34. 2024RB-SQL: A Retrieval-based LLM Framework for Text-to-SQLcited by 3
  35. 2023T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Training Report of TeleChat3-MoEcited by 4
  2. 2026Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editingcited by 4
  3. 2026Dynamic Knowledge Fusion for Multi-Domain Dialogue State Trackingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering
  2. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  3. 2025TableReasoner: Advancing Table Reasoning Framework with Large Language Models
  4. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering
  5. 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios
  6. 2025A Survey of Large Language Model Agents for Question Answering
  7. 2026Accurate Table Question Answering with Accessible LLMs
  8. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation