SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation

TL;DR

SheetMind is a multi-agent framework utilizing large language models to automate spreadsheet tasks through natural language, enabling real-time, script-free interactions in Google Sheets with high success rates.

Contribution

This paper introduces a novel multi-agent system that decomposes, translates, and validates natural language instructions for spreadsheet automation, integrating seamlessly with Google Sheets.

Findings

Achieves 80% success on single-step tasks

Reaches 70% success on multi-step instructions

Outperforms baseline and ablated variants

Abstract

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.