mlsanityData to 7 Oct 2026

DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering

arXiv 2603.09152 ↗First posted 10 Mar 2026cs.AI cs.DB cs.IRcited by 0

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

Abstract (arXiv)

Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling capabilities, hallucination issues that compromise answer reliability, and single-agent architectures that struggle with complex reasoning scenarios involving semantic relationships and multi-hop logic. This paper introduces DataFactory, a multi-agent framework that addresses these limitations through specialized team coordination and automated knowledge transformation. The framework comprises a Data Leader employing the ReAct paradigm for reasoning orchestration, together with dedicated Database and Knowledge Graph teams, enabling the systematic decomposition of complex queries into structured and relational reasoning tasks. We formalize automated data-to-knowledge graph transformation via the mapping function T:D x S x R -> G, and implement natural language-based consultation that - unlike fixed workflow multi-agent systems - enables flexible inter-agent deliberation and adaptive planning to improve coordination robustness. We also apply context engineering strategies that integrate historical patterns and domain knowledge to reduce hallucinations and improve query accuracy. Across TabFact, WikiTableQuestions, and FeTaQA, using eight LLMs from five providers, results show consistent gains. Our approach improves accuracy by 20.2% (TabFact) and 23.9% (WikiTQ) over baselines, with significant effects (Cohen's d > 1). Team coordination also outperforms single-team variants (+5.5% TabFact, +14.4% WikiTQ, +17.1% FeTaQA ROUGE-2). The framework offers design guidelines for multi-agent collaboration and a practical platform for enterprise data analysis through integrated structured querying and graph-based knowledge representation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 44 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

27 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering28 Dec
  2. 2024AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework10 Dec

Other references · 25

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  3. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  4. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  5. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  6. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  7. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  8. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  9. 2020Open Question Answering over Tables and Textcited by 163
  10. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  11. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  12. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
13 more
  1. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  2. 2024Large Language Model for Table Processing: A Surveycited by 52
  3. 2023Tab-CoT: Zero-shot Tabular Chain of Thoughtcited by 42
  4. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  5. 2025Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoningcited by 32
  6. 2023Large Language Models are Complex Table Parserscited by 28
  7. 2025Table-R1: Inference-Time Scaling for Table Reasoningcited by 23
  8. 2024GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answeringcited by 18
  9. 2024Interpretable LLM-based Table Question Answeringcited by 18
  10. 2023API-Assisted Code Generation for Question Answering on Varied Table Structurescited by 14
  11. 2025Weaver: Interweaving SQL and LLM for Table Reasoningcited by 8
  12. 2024Table Question Answering for Low-resourced Indic Languagescited by 7
  13. 2025General Table Question Answering via Answer-Formula Joint Generationcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  2. 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering
  3. 2025Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance
  4. 2025ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning
  5. 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering
  6. 2025Agentic LLMs for Question Answering over Tabular Data
  7. 2026Towards Researcher Agents for Knowledge-Graph Question Answering
  8. 2023On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering