Skip to content

Latest commit

 

History

History
78 lines (50 loc) · 2.98 KB

change_readme_here.md

File metadata and controls

78 lines (50 loc) · 2.98 KB

Awesome GUI Agent Paper List (Work-In-Progress)

Paper Covrage:

A variety of papers related to GUI Agents, including but not limited to:

  • GUI Understanding
  • Datasets
  • Benchmarks
  • New frameworks
  • New models
  • Vision, language, multimodal foundation models (with explicit support for GUI)
  • Works in the General Domain extensively used by GUI Agents (e.g., SoM prompting)

Updates

  • December 7, 2024: Moved the ownership to OSU-NLP-Group

All Papers (from most recent to oldest)

{{insert_content_here}}

Tutorials, Talks, Blogs

Project & Software

Related Repositories

How to Add a Paper

TODO: Move the details to the bottom later. Also add a ToC.

format example:

- [title](paper link)
    - List authors directly without a "key" identifier (e.g., author1, author2)
    - 🏛️ Institutions: List the institutions concisely, using abbreviations (e.g., university names, like OSU).
    - 📅 Date: e.g., Oct 30, 2024
    - 📑 Publisher: ICLR 2025
    - 💻 Env: Indicate the research environment within brackets, such as [Web], [Mobile], or [Desktop]. Use [GUI] if the research spans multiple environments. Use [General] if it is researching on general domains.
    - 🔑 Key: Label each keyword within brackets, e.g., [model], [framework],[dataset],[benchmark].
    - 📖 TLDR: Brief summary of the paper.

Regarding the 🔑 Key:

  • model: Indicates a newly trained model.
  • framework: If the paper proposes a new framework.
  • dataset: If a new dataset is created and published.
  • benchmark: If a new benchmark is established (add "dataset" if there's a new training set).
  • primary Innovation: List the main focus or innovation in the study.
  • Common Abbreviations: Include commonly used abbreviations associated with the paper. (model names, framework names, etc.)

For missing information, use "Unknown."

You can contribute by providing either the paper title or a fully formatted entry in Paper Collection. You’re also welcome to open a new PR with your submission.

For ease of use, you can use this GPTs to help search your paper and format the entry automatically. (prompts in auto_prompt.txt)

TODO: Add subgroups here (benchmark, datasets, models, learning, safety, framework, etc.

Contributors