ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios
Abstract
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.
Keywords
Cite
@article{arxiv.2601.07280,
title = {ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios},
author = {Changzai Pan and Jie Zhang and Kaiwen Wei and Chenshuo Pan and Yu Zhao and Jingwang Huang and Jian Yang and Zhenhe Wu and Haoyang Zeng and Xiaoyan Gu and Weichao Sun and Yanbo Zhai and Yujie Mao and Zhuoru Jiang and Jiang Zhong and Shuangyong Song and Yongxiang Li and Zhongjiang He},
journal= {arXiv preprint arXiv:2601.07280},
year = {2026}
}