Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.12339 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912429889290240 |
|---|---|
| author | Zhu, Ruiyan Cheng, Xi Liu, Ke Zhu, Brian Jin, Daniel Parihar, Neeraj Xu, Zhoutian Gao, Oliver |
| author_facet | Zhu, Ruiyan Cheng, Xi Liu, Ke Zhu, Brian Jin, Daniel Parihar, Neeraj Xu, Zhoutian Gao, Oliver |
| contents | We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions. The system comprises three specialized agents: a Manager Agent that decomposes complex user instructions into subtasks; an Action Agent that translates these into structured commands using a Backus Naur Form (BNF) grammar; and a Reflection Agent that validates alignment between generated actions and the user's original intent. Integrated into Google Sheets via a Workspace extension, SheetMind supports real-time interaction without requiring scripting or formula knowledge. Experiments on benchmark datasets demonstrate an 80 percent success rate on single step tasks and approximately 70 percent on multi step instructions, outperforming ablated and baseline variants. Our results highlight the effectiveness of multi agent decomposition and grammar based execution for bridging natural language and spreadsheet functionalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12339 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation Zhu, Ruiyan Cheng, Xi Liu, Ke Zhu, Brian Jin, Daniel Parihar, Neeraj Xu, Zhoutian Gao, Oliver Human-Computer Interaction Artificial Intelligence We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions. The system comprises three specialized agents: a Manager Agent that decomposes complex user instructions into subtasks; an Action Agent that translates these into structured commands using a Backus Naur Form (BNF) grammar; and a Reflection Agent that validates alignment between generated actions and the user's original intent. Integrated into Google Sheets via a Workspace extension, SheetMind supports real-time interaction without requiring scripting or formula knowledge. Experiments on benchmark datasets demonstrate an 80 percent success rate on single step tasks and approximately 70 percent on multi step instructions, outperforming ablated and baseline variants. Our results highlight the effectiveness of multi agent decomposition and grammar based execution for bridging natural language and spreadsheet functionalities. |
| title | SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2506.12339 |