{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sheetagent-a-generalist-agent-for-spreadsheet","title":"SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models","arxiv_id":"2403.03636","date":"2024-03-06","proceeding":null,"authors":["Yibin Chen","Yifu Yuan","Zeyu Zhang","Yan Zheng","Jinyi Liu","Fei Ni","Jianye Hao"],"abstract":"Spreadsheet manipulation is widely existing in most daily works and significantly improves working efficiency. 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 $\\textbf{SheetRM}$, 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 $\\textbf{SheetAgent}$, a novel autonomous agent that utilizes the power of LLMs. SheetAgent consists of three collaborative modules: $\\textit{Planner}$, $\\textit{Informer}$, and $\\textit{Retriever}$, 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.","url_abs":"https://arxiv.org/abs/2403.03636v2","url_pdf":"https://arxiv.org/pdf/2403.03636v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"robot-task-planning","task_name":"Robot Task Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robot-task-planning-on-sheetcopilot","task":"Robot Task Planning","dataset":"SheetCopilot","model":"SheetAgent (GPT-3.5)","rank_in_archive_order":1,"of":2,"metrics":{"Pass@1":"61.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.03636","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}