构建表格关系图谱，让AI理解多表复杂结构并高效推理
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
- 用图结构显式建模表内表间关系，保留空间布局信息
- 结合记忆机制，支持跨表关联的长期依赖推理
- 适合处理含复杂依赖的金融、报表类自动化任务
电子表格广泛用于组织、分析和操作半结构化数据，但大语言模型（LLMs）在自动化表格推理方面仍面临挑战。真实工作簿常包含隐式跨表关联、细粒度列依赖关系以及复杂的空间布局。现有方法通常将多维结构扁平化为序列字符串，丢失了表内边界与表间语义。因此，LLMs无法利用人类专家检查表格时自然具备的全局空间上下文。我们提出 SheetCompass，一种基于图引导且内存驱动的代理框架，用于表格推理与自动化。该框架显式建模工作表内部及跨工作表的结构关系，同时在内存中保持任务相关的信息，使智能体能更有效地处理复杂工作簿。
原文摘要 · Abstract (English)
Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks often contain implicit cross-table associations, fine-grained column dependencies, and complex spatial layouts. Existing methods typically flatten these multidimensional structures into sequential strings, losing important intra-sheet boundaries and inter-sheet semantics. Consequently, LLMs cannot exploit the global spatial context that human experts naturally use when inspecting spreadsheets. We propose SheetCompass, a graph-guided and memory-driven agentic framework for spreadsheet reasoning and automation. SheetCompass explicitly models structural relationships within and across worksheets while maintaining task-relevant information in memory, enabling agents to reason more effectively over complex workbooks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。