SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning

• URL: http://arxiv.org/abs/2608.14452v1
• Date: Fri, 14 Aug 2026 16:39:16 GMT
• Title: SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
• Abstract summary: We propose Sheet, a graph-guided and memory-driven framework for spreadsheet reasoning and automation.<n>Sheet explicitly models structural relationships within and across worksheets while maintaining task-relevant information in memory.
• Score: 13.891450098227573
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Sheet as Token: A Graph-Enhanced Representation for Multi-Sheet Spreadsheet Understanding [14.27017655999633]
  Sheet as Token is a graph-enhanced framework that treats each worksheet as a unified semantic unit for multi-sheet spreadsheet retrieval.<n>A Graph Retriever constructs a query-specific candidate graph over sheet tokens using semantic, query-conditioned, schema-consistency, and shape-compatibility relations.<n>Experiments on a constructed multi-sheet spreadsheet corpus show that sheet-level tokenization learns stable representations.
  arXiv  Detail & Related papers  (2026-05-07T07:47:43Z)
• Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning [43.91509663025854]
  Spreadsheets are central to real-world applications such as enterprise reporting, auditing, and scientific data management.<n>Existing large language model based approaches typically treat tables as plain text, overlooking critical layout cues and visual semantics.<n>We propose a two-stage multi-agent framework for spreadsheet understanding that adopts a step-by-step reading and reasoning paradigm.
  arXiv  Detail & Related papers  (2026-04-14T04:47:21Z)
• TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment [70.83664203825235]
  TDATR (Table Detail-Aware Table Recognition) improves end-to-end TR through table detail-aware learning and cell-level visual alignment.<n>We achieve state-of-the-art or highly competitive performance on seven benchmarks without dataset-specific fine-tuning.
  arXiv  Detail & Related papers  (2026-03-24T05:45:02Z)
• SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks [8.306042091008957]
  Large language models (LLMs) are increasingly tasked with producing and manipulating structured artifacts.<n>We introduce SpreadsheetArena, a platform for evaluating models' performance on the task.<n>We observe that stylistic, structural, and functional features of preferred spreadsheets vary substantially across use cases.
  arXiv  Detail & Related papers  (2026-02-16T14:24:36Z)
• How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location [53.68149869349268]
  We investigate the process of table understanding by dissecting the atomic task of cell location.<n>We demonstrate that models locate the target cell via an ordinal mechanism that counts discretes to resolve coordinates.<n>We reveal that models generalize to multi-cell location tasks by multiplexing the identical attention heads identified during atomic location.
  arXiv  Detail & Related papers  (2026-02-09T11:47:34Z)
• SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection [26.315814679351988]
  SheetDesigner is a zero-shot framework that combines rule and vision reflection for component placement and content population.<n>We find that through vision modality, MLLMs handle overlap and balance well but struggle with alignment.
  arXiv  Detail & Related papers  (2025-09-09T07:51:38Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation [34.8332394229927]
  SpreadsheetBench is designed to immerse current large language models (LLMs) in the actual workflow of spreadsheet users. Unlike existing benchmarks that rely on synthesized queries and simplified spreadsheet files, SpreadsheetBench is built from 912 real questions gathered from online Excel forums. Our comprehensive evaluation of various LLMs under both single-round and multi-round inference settings reveals a substantial gap between the state-of-the-art (SOTA) models and human performance.
  arXiv  Detail & Related papers  (2024-06-21T09:06:45Z)
• TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios [51.66718740300016]
  TableLLM is a robust large language model (LLM) with 8 billion parameters.<n>TableLLM is purpose-built for proficiently handling data manipulation tasks.<n>We have released the model checkpoint, source code, benchmarks, and a web application for user interaction.
  arXiv  Detail & Related papers  (2024-03-28T11:21:12Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• SpreadsheetCoder: Formula Prediction from Semi-structured Context [70.41579328458116]
  We propose a BERT-based model architecture to represent the tabular context in both row-based and column-based formats. We train our model on a large dataset of spreadsheets, and demonstrate that SpreadsheetCoder achieves top-1 prediction accuracy of 42.51%. Compared to the rule-based system, SpreadsheetCoder 82% assists more users in composing formulas on Google Sheets.
  arXiv  Detail & Related papers  (2021-06-26T11:26:27Z)
• A Graph Representation of Semi-structured Data for Web Question Answering [96.46484690047491]
  We propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-10-14T04:01:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.