# SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning

arXiv: https://arxiv.org/abs/2608.14452 · HTML: https://mlsanity.com/paper/2608.14452/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 67 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [Cumulative Reasoning with Large Language Models](https://mlsanity.com/paper/2308.04371/) (2023)
- [Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples](https://mlsanity.com/paper/1804.01186/) (2018)
- [SpreadsheetLLM: Encoding Spreadsheets for Large Language Models](https://mlsanity.com/paper/2407.09025/) (2024)
- [PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables](https://mlsanity.com/paper/2412.04272/) (2024)
- [Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning](https://mlsanity.com/paper/2604.12282/) (2026)
- [All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction](https://mlsanity.com/paper/2601.04567/) (2026)

## Abstract (arXiv)

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.