SheetAgent: Towards 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, Hangyu Mao, Fuzheng Zhang

Track: Semantics and knowledge

Keywords: Agents, Large Language Models, Benchmark, Spreadsheet Reasoning and Manipulation

TL;DR: We propose SheetAgent, a generalist language agent for spreadsheet reasoning and manipulation, along with a curated benchmark SheetRM with real-life spreadsheet tasks.

Abstract: Spreadsheets are ubiquitous across the World Wide Web, playing a critical role in enhancing work efficiency across various domains. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has 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**, a 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 20-40\% 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. The datasets and source code are available at https://anonymous.4open.science/r/SheetAgent.

Submission Number: 1228