Scholarlink

<p>Tables are widely used across various domains such as finance, healthcare, and chemistry, playing a critical role in modern applications. While recent advances in <b>Large Language Models (LLMs)</b> like GPT-4 have opened new possibilities for handling table tasks, existing research predominantly focuses on clean, academic datasets, which do not reflect the complexity of real-world table data. Real-world table tasks are often characterized by noise, structural diversity, and semantic intricacy, posing challenges for effective automation. This survey focuses on <b>LLM-based Table Agents</b>, which aim to automate table-centric workflows by integrating preprocessing, reasoning, and domain adaptation. We define five core competencies—<b>C1:</b> Table Structure Understanding, <b>C2:</b> Table and Query Semantic Understanding, <b>C3:</b> Table Retrieval and Compression, <b>C4:</b> Executable Reasoning with Traceability, and <b>C5:</b> Cross-Domain Generalization—to analyze and compare current approaches. In addition, a detailed examination of the Text-to-SQL Agent reveals a performance gap between academic benchmarks and real-world scenarios, especially for open-source models. Finally, we provide actionable insights to improve the robustness, generalization, and efficiency of LLM-based Table Agents in practical settings.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Toward real-world Table Agents: capabilities, workflows, and design principles for LLM-based table intelligence

  • 期刊论文

  • 发表日期：

    2026年1月20日

查看全文
  • Jiaming Tian,
  • Liyao Li,
  • Wentao Ye,
  • Haobo Wang,
  • Lingxin Wang,
  • Lihua Yu,
  • Zujie Ren,
  • Gang Chen,
  • Junbo Zhao

摘要

Tables are widely used across various domains such as finance, healthcare, and chemistry, playing a critical role in modern applications. While recent advances in Large Language Models (LLMs) like GPT-4 have opened new possibilities for handling table tasks, existing research predominantly focuses on clean, academic datasets, which do not reflect the complexity of real-world table data. Real-world table tasks are often characterized by noise, structural diversity, and semantic intricacy, posing challenges for effective automation. This survey focuses on LLM-based Table Agents, which aim to automate table-centric workflows by integrating preprocessing, reasoning, and domain adaptation. We define five core competencies—C1: Table Structure Understanding, C2: Table and Query Semantic Understanding, C3: Table Retrieval and Compression, C4: Executable Reasoning with Traceability, and C5: Cross-Domain Generalization—to analyze and compare current approaches. In addition, a detailed examination of the Text-to-SQL Agent reveals a performance gap between academic benchmarks and real-world scenarios, especially for open-source models. Finally, we provide actionable insights to improve the robustness, generalization, and efficiency of LLM-based Table Agents in practical settings.