arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.09151cs.AI
收藏

通过持续经验驱动执行进行深度表格研究

Deep Tabular Research via Continual Experience-Driven Execution

Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang

AI总结:

本文提出深度表格研究(DTR)框架,通过闭环决策过程解决复杂表格分析问题,利用分层元图和期望感知策略实现持续优化,验证了战略规划与低层执行分离的重要性。

摘要:

大型语言模型在处理涉及无结构表格的复杂长周期分析任务时往往表现不佳,这些表格通常具有层次化和双向表头以及非标准布局。我们将这一挑战正式定义为深度表格研究(DTR),需要在相互依赖的表格区域上进行多步骤推理。为了解决DTR问题,我们提出了一种新的代理框架,将表格推理视为闭环决策过程。我们精心设计了耦合的查询和表格理解机制用于路径决策和操作执行。具体而言,(i) DTR首先构建一个分层元图来捕捉双向语义,将自然语言查询映射到操作级搜索空间;(ii) 为了导航此空间,我们引入了期望感知的选择策略,优先选择高效益的执行路径;(iii) 关键在于将历史执行结果合成到siamese结构化记忆中,即参数化更新和抽象化的文本,实现持续优化。在具有挑战性的无结构表格基准上进行了广泛的实验,验证了有效性,并突显了为长周期表格推理分离战略规划与低层执行的必要性。

英文摘要:

Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑