mlsanityData to 14 Oct 2026

JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models

arXiv 2512.06859 ↗First posted 7 Dec 2025cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

In this work, we present JT-DA-8B (JiuTian Data Analyst 8B), a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios. To address the lack of high-quality supervision in tabular reasoning scenarios, we construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables. An automatic pipeline is proposed to generate realistic multi-step analytical tasks involving reasoning patterns. The model is trained upon open-source JT-Coder-8B model, an 8B-parameter decoder-only foundation model trained from scratch. In the training stage, we leverage LLM-based scoring and workflow-aligned filtering to distill high-quality, table-centric data. Both supervised fine-tuning (SFT) and Reinforcement learning (RL) are adopted to optimize our model. Afterwards, a four-stage table reasoning workflow is proposed, including table preprocessing, table sensing, tool-integrated reasoning, and prompt engineering, to improve model interpretability and execution accuracy. Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks, demonstrating the effectiveness of data-centric generation and workflow-driven optimization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 65 of its 73 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

65 of 73 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models23 Jun
  2. 2025Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models6 Jun
  3. 2025Table-R1: Inference-Time Scaling for Table Reasoning29 May
  4. 2025Table-R1: Region-based Reinforcement Learning for Table Understanding18 May
  5. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding9 Jan
  6. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan
  7. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples22 Oct

Other references · 58

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2024Qwen2.5 Technical Reportcited by 4,942
  10. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  11. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  12. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
38 more
  1. 2023Mistral 7Bcited by 3,164
  2. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  3. 2019Root Mean Square Layer Normalizationcited by 1,480
  4. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,346
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  9. 2024Yi: Open Foundation Models by 01.AIcited by 719
  10. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  11. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 464
  12. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
  13. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 268
  14. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  15. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 232
  16. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 148
  17. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
  18. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 128
  19. 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?cited by 125
  20. 2024MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmarkcited by 105
  21. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 102
  22. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLcited by 87
  23. 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 81
  24. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 77
  25. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  26. 2023Is GPT-4 a Good Data Analyst?cited by 70
  27. 2023MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Taskscited by 66
  28. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  29. 2021AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industrycited by 44
  30. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  31. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 41
  32. 2023Large Language Models as Data Preprocessorscited by 34
  33. 2024Efficient Tool Use with Chain-of-Abstraction Reasoningcited by 33
  34. 2025Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoningcited by 32
  35. 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 27
  36. 2023LogGPT: Log Anomaly Detection via GPTcited by 26
  37. 2023UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generationcited by 22
  38. 2023Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration Systemcited by 20

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
  2. 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models
  3. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
  4. 2023Rethinking Tabular Data Understanding with Large Language Models
  5. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards
  6. 2025TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
  7. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
  8. 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm