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.

翻译：本文提出JT-DA-8B（九天数据分析师8B），一种专为多样化现实场景中复杂表格推理任务设计的专业化大语言模型。为解决表格推理场景中高质量监督数据的不足，我们通过整合29个公开表格问答数据集及300万张表格，构建了一个涵盖34项明确定义的表格推理任务的全面且多样化的训练语料库。提出了一种自动化流水线以生成涉及推理模式的真实多步骤分析任务。该模型基于开源的JT-Coder-8B模型（一个从头训练的80亿参数仅解码器基础模型）进行训练。在训练阶段，我们利用基于大语言模型的评分和与工作流对齐的过滤机制，蒸馏出高质量的表格中心数据。采用监督微调（SFT）和强化学习（RL）共同优化模型。随后，提出了包含表格预处理、表格感知、工具集成推理和提示工程的四阶段表格推理工作流，以提升模型可解释性和执行准确性。实验结果表明，JT-DA-8B在多种表格推理任务中均取得优异性能，验证了以数据为中心的生成方法与工作流驱动优化策略的有效性。