Recent advancements in Large Language Models (LLMs) have significantly catalyzed table-based question answering (TableQA). However, existing TableQA benchmarks often overlook the intricacies of industrial scenarios, which are characterized by multi-table structures, nested headers, and massive scales. These environments demand robust table reasoning through deep structured inference, presenting a significant challenge that remains inadequately addressed by current methodologies. To bridge this gap, we present ReasonTabQA, a large-scale bilingual benchmark encompassing 1,932 tables across 30 industry domains such as energy and automotive. ReasonTabQA provides high-quality annotations for both final answers and explicit reasoning chains, supporting both thinking and no-thinking paradigms. Furthermore, we introduce TabCodeRL, a reinforcement learning method that leverages table-aware verifiable rewards to guide the generation of logical reasoning paths. Extensive experiments on ReasonTabQA and 4 TableQA datasets demonstrate that while TabCodeRL yields substantial performance gains on open-source LLMs, the persistent performance gap on ReasonTabQA underscores the inherent complexity of real-world industrial TableQA.

翻译：近年来，大型语言模型（LLMs）的进展显著推动了基于表格的问答（TableQA）的发展。然而，现有的TableQA基准往往忽略了工业场景的复杂性，这些场景通常具有多表结构、嵌套表头和海量规模等特点。此类环境要求通过深层结构化推理进行鲁棒的表格理解，这对当前方法构成了重大挑战，且尚未得到充分解决。为弥补这一差距，我们提出了ReasonTabQA，这是一个大规模双语基准，涵盖能源、汽车等30个行业领域的1,932张表格。ReasonTabQA为最终答案和显式推理链提供了高质量标注，同时支持思维链与非思维链两种范式。此外，我们提出了TabCodeRL，一种利用表格感知可验证奖励来引导逻辑推理路径生成的强化学习方法。在ReasonTabQA及4个TableQA数据集上的大量实验表明，尽管TabCodeRL在开源LLMs上带来了显著的性能提升，但在ReasonTabQA上持续存在的性能差距凸显了真实世界工业TableQA固有的复杂性。