SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models

Yibin Chen, Yifu Yuan, Zeyu Zhang, YAN ZHENG, Jinyi Liu, Fei Ni, Jianye HAO

Keywords: Large Language Models, Autonomous Agent, Benchmark, Spreadsheet Manipulation

TL;DR: We propose SheetAgent, a generalist agent for spreadsheet reasoning and manipulation.

Abstract: Spreadsheet manipulation is widely-existing in most daily works and significantly improves the working efficiency. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation, but not yet been investigated in complicated and realistic tasks where reasoning challenges exist (e.g., long horizon manipulation with multi-step reasoning and ambiguous requirements). To bridge the gap with the real-world requirements, we introduce **SheetRM**, a benchmark featuring long-horizon and multi-category tasks with reasoning dependent manipulation caused by real-life challenges. To mitigate the above challenges, we further propose **SheetAgent**, an novel autonomous agent that utilizes the power of LLMs. SheetAgent consists of three collaborative modules: Planner, Informer and Retriever, achieving both advanced reasoning and accurate manipulation over spreadsheets without human interaction through iterative task reasoning and reflection. Extensive experiments demonstrate that SheetAgent delivers 20-30% pass rate improvements on multiple benchmarks over baselines, achieving enhanced precision in spreadsheet manipulation and demonstrating superior table reasoning abilities. More details and visualizations are available at https://sheetagent.github.io.

Submission Number: 2