SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets

• URL: http://arxiv.org/abs/2510.19247v1
• Date: Wed, 22 Oct 2025 05:09:44 GMT
• Title: SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets
• Authors: Ziwei Wang, Jiayuan Su, Mengyu Zhou, Huaxing Zeng, Mengni Jia, Xiao Lv, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang,
• Abstract summary: SheetBrain is a neuro-symbolic dual agent framework for reasoning over spreadsheets.<n>It supports both spreadsheet question answering and manipulation tasks.<n>We introduce SheetBench, a new benchmark targeting large, multi-table, and structurally complex spreadsheets.
• Score: 37.47629183214491
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding and reasoning over complex spreadsheets remain fundamental challenges for large language models (LLMs), which often struggle with accurately capturing the complex structure of tables and ensuring reasoning correctness. In this work, we propose SheetBrain, a neuro-symbolic dual workflow agent framework designed for accurate reasoning over tabular data, supporting both spreadsheet question answering and manipulation tasks. SheetBrain comprises three core modules: an understanding module, which produces a comprehensive overview of the spreadsheet - including sheet summary and query-based problem insight to guide reasoning; an execution module, which integrates a Python sandbox with preloaded table-processing libraries and an Excel helper toolkit for effective multi-turn reasoning; and a validation module, which verifies the correctness of reasoning and answers, triggering re-execution when necessary. We evaluate SheetBrain on multiple public tabular QA and manipulation benchmarks, and introduce SheetBench, a new benchmark targeting large, multi-table, and structurally complex spreadsheets. Experimental results show that SheetBrain significantly improves accuracy on both existing benchmarks and the more challenging scenarios presented in SheetBench. Our code is publicly available at https://github.com/microsoft/SheetBrain.

Related papers

• SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats [0.0]
  SQuARE is a hybrid retrieval framework with sheet-level, complexity-aware routing.<n>It computes a continuous score based on header depth and merge density.<n>SQuARE consistently surpasses single-strategy baselines and ChatGPT-4o on both retrieval precision and end-to-end answer accuracy.
  arXiv  Detail & Related papers  (2025-12-03T22:11:45Z)
• General Table Question Answering via Answer-Formula Joint Generation [48.004786816436116]
  Advanced table question answering (TableQA) methods prompt large language models (LLMs) to generate answer text or Python code.<n>These methods lack the versatility to cope with specific question types or table structures.<n>We propose textttTabAF, a general table answering framework to solve multiple types of tasks over multiple types of tables simultaneously.<n>Under the same model size, textttTabAF achieves new state-of-the-art performance on the WikiTable, HiTab, and TabFact.
  arXiv  Detail & Related papers  (2025-03-16T03:51:06Z)
• 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)
• SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models [45.930510174309845]
  Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation.<n>SheetAgent consists of three collaborative modules: Planner, Informer, and Retriever.<n>Extensive experiments demonstrate that SheetAgent delivers 20--40% pass rate improvements on multiple benchmarks over baselines.
  arXiv  Detail & Related papers  (2024-03-06T11:48:08Z)
• 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)
• MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering [61.48881995121938]
  Real-world queries are complex in nature, often over multiple tables in a relational database or web page. Our model, MultiTabQA, not only answers questions over multiple tables, but also generalizes to generate tabular answers.
  arXiv  Detail & Related papers  (2023-05-22T08:25:15Z)
• Enhanced Spreadsheet Computing with Finite-Domain Constraint Satisfaction [1.6244541005112747]
  We present an enhanced spreadsheet system where finite-domain constraint solving is well supported in a visual environment. A spreadsheet-specific constraint language is constructed for general users to specify constraints among data cells. The new spreadsheet system significantly simplifies the development of many constraint-based applications.
  arXiv  Detail & Related papers  (2022-02-22T17:58:08Z)
• Spreadsheet computing with Finite Domain Constraint Enhancements [0.0]
  We present a framework seamlessly incorporating a finite constraint solver with the spreadsheet computing paradigm. The framework provides an interface for constraint solving and further enhances the spreadsheet computing paradigm.
  arXiv  Detail & Related papers  (2022-02-22T17:50:48Z)
• 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)

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.