SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models
Hongxin Li, Jingran Su, Yuntao Chen, Qing Li, Zhaoxiang Zhang
- 🏛 Institutions
- University of Chinese Academy of Sciences, Hong Kong Institute of Science and Innovation, CAS, PolyU, Shanghai AI Laboratory
- 📅 Date
- May 30, 2023
- 📑 Publisher
- NeurIPS 2023
- 💻 Env
- General GUI
- 🔑 Keywords
TLDR
SheetCopilot studies spreadsheet control with an LLM agent that plans over a state-machine abstraction of spreadsheet operations. The paper also releases a 221-task spreadsheet-control dataset and an automated evaluation pipeline for benchmarking software-control performance.
Related papers
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration BenchmarkApril 18, 2025 · arXiv
- Grounding Open-Domain Instructions to Automate Web Support TasksMarch 30, 2021 · NAACL 2021
- LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI AgentJanuary 26, 2026 · ICLR 2026 (Poster)
- GUIGuard: Toward a General Framework for Privacy-Preserving GUI AgentsJanuary 26, 2026 · arXiv
- Beyond Clicking: A Step Towards Generalist GUI Grounding via Text DraggingNovember 7, 2025 · arXiv
- Scaling Computer‑Use Grounding via User Interface Decomposition and SynthesisMay 19, 2025 · NeurIPS 2025 Datasets and Benchmarks Track (Spotlight)