Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.19247 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914107657027584 |
|---|---|
| author | Wang, Ziwei Su, Jiayuan Zhou, Mengyu Zeng, Huaxing Jia, Mengni Lv, Xiao Dong, Haoyu Ma, Xiaojun Han, Shi Zhang, Dongmei |
| author_facet | Wang, Ziwei Su, Jiayuan Zhou, Mengyu Zeng, Huaxing Jia, Mengni Lv, Xiao Dong, Haoyu Ma, Xiaojun Han, Shi Zhang, Dongmei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19247 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets Wang, Ziwei Su, Jiayuan Zhou, Mengyu Zeng, Huaxing Jia, Mengni Lv, Xiao Dong, Haoyu Ma, Xiaojun Han, Shi Zhang, Dongmei Computation and Language 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. |
| title | SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.19247 |