SheetCompass：面向智能体电子表格推理的分层关系图
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
浏览论文内容
中文总结 AI 辅助
针对LLM处理电子表格时丢失多维结构语义的问题，提出SheetCompass框架，通过显式建模表内外结构关系并结合内存机制，提升智能体对复杂工作簿的推理能力。
中文摘要 AI 辅助
电子表格被广泛用于组织、分析和处理半结构化数据，但大型语言模型（LLM）的自动化电子表格推理仍具挑战性。实际工作簿常包含隐式的跨表关联、细粒度列依赖及复杂空间布局，现有方法通常将这些多维结构展平为顺序字符串，丢失了重要的表内边界和表间语义，导致LLM无法利用人类专家检查电子表格时自然使用的全局空间上下文。我们提出SheetCompass，一种图引导、记忆驱动的智能体框架，用于电子表格推理与自动化，该框架显式建模工作表内部及跨工作表的结构关系，同时在内存中保留任务相关信息，使智能体能对复杂工作簿进行更有效的推理。
英文摘要
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.
发表机构
- University of Science and Technology of China（中国科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。
