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

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

Abstract: 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.

External IDs:dblp:journals/www/TianLYWWYRCZ26