Saved in:
Bibliographic Details
Main Authors: Gulati, Anmol, Sen, Sahil, Sarguroh, Waqar, Paul, Kevin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917258783096832
author Gulati, Anmol
Sen, Sahil
Sarguroh, Waqar
Paul, Kevin
author_facet Gulati, Anmol
Sen, Sahil
Sarguroh, Waqar
Paul, Kevin
contents Large Language Models (LLMs) struggle to reason over large-scale enterprise spreadsheets containing thousands of numeric rows, multiple linked sheets, and embedded visual content such as charts and receipts. Prior state-of-the-art spreadsheet reasoning approaches typically rely on single-sheet compression or full-context encoding, which limits scalability and fails to reflect how real users interact with complex, multimodal workbooks. We introduce FRTR-Bench, the first large-scale benchmark for multimodal spreadsheet reasoning, comprising 30 enterprise-grade Excel workbooks spanning nearly four million cells and more than 50 embedded images. To address these challenges, we present From Rows to Reasoning (FRTR), an advanced, multimodal retrieval-augmented generation framework that decomposes Excel workbooks into granular row, column, and block embeddings, employs hybrid lexical-dense retrieval with Reciprocal Rank Fusion (RRF), and integrates multimodal embeddings to reason over both numerical and visual information. We tested FRTR on six LLMs, achieving 74% answer accuracy on FRTR-Bench with Claude Sonnet 4.5, a substantial improvement over prior state-of-the-art approaches that reached only 24%. On the SpreadsheetLLM benchmark, FRTR achieved 87% accuracy with GPT-5 while reducing token usage by roughly 50% compared to direct serialization methods.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08741
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Rows to Reasoning: A Retrieval-Augmented Multimodal Framework for Spreadsheet Understanding
Gulati, Anmol
Sen, Sahil
Sarguroh, Waqar
Paul, Kevin
Computation and Language
Large Language Models (LLMs) struggle to reason over large-scale enterprise spreadsheets containing thousands of numeric rows, multiple linked sheets, and embedded visual content such as charts and receipts. Prior state-of-the-art spreadsheet reasoning approaches typically rely on single-sheet compression or full-context encoding, which limits scalability and fails to reflect how real users interact with complex, multimodal workbooks. We introduce FRTR-Bench, the first large-scale benchmark for multimodal spreadsheet reasoning, comprising 30 enterprise-grade Excel workbooks spanning nearly four million cells and more than 50 embedded images. To address these challenges, we present From Rows to Reasoning (FRTR), an advanced, multimodal retrieval-augmented generation framework that decomposes Excel workbooks into granular row, column, and block embeddings, employs hybrid lexical-dense retrieval with Reciprocal Rank Fusion (RRF), and integrates multimodal embeddings to reason over both numerical and visual information. We tested FRTR on six LLMs, achieving 74% answer accuracy on FRTR-Bench with Claude Sonnet 4.5, a substantial improvement over prior state-of-the-art approaches that reached only 24%. On the SpreadsheetLLM benchmark, FRTR achieved 87% accuracy with GPT-5 while reducing token usage by roughly 50% compared to direct serialization methods.
title From Rows to Reasoning: A Retrieval-Augmented Multimodal Framework for Spreadsheet Understanding
topic Computation and Language
url https://arxiv.org/abs/2601.08741