{
  "annotation_id": "adf65702-6fa4-461c-95dc-32c6d1854853",
  "date_created": "2026-02-17T05:53:15.690000Z",
  "date_modified": "2026-02-17T05:53:15.690000Z",
  "file_hash": "00e4762010e1303c0b15b81c4266003fd1a6e94c6ff2d1564c8b0f07e42ebc39",
  "private": false,
  "record": {
    "abstract": "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 context-compression methods.",
    "arxiv_id": "2601.08741",
    "authors": [
      "Anmol Gulati",
      "Sahil Sen",
      "Waqar Sarguroh",
      "Kevin Paul"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "From Rows to Reasoning: A Retrieval-Augmented Multimodal Framework for Spreadsheet Understanding",
    "url": "https://arxiv.org/abs/2601.08741",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "5e656562-e732-4972-861c-e6a4ef8b0fc3",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}