Skip to content

Adding project homepage #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michael0402 merged 3 commits into from
Jan 27, 2026
Merged

Adding project homepage #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1bb2e6e
adding v0 of project homepage
michael0402 Jan 27, 2026
ea54ede
making graph smaller
michael0402 Jan 27, 2026
080c673
adding bibtext
michael0402 Jan 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
285 changes: 285 additions & 0 deletions docs/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,285 @@
<!DOCTYPE html>
<html>

<head>
<meta charset="utf-8">
<!-- Meta tags for social media banners, these should be filled in appropriatly as they are your "business card" -->
<!-- Replace the content tag with appropriate information -->
<meta name="description" content="A project homepage for CUA-Skill">
<meta property="og:title" content="CUA-Skill" />
<meta property="og:description" content="A project homepage for CUA-Skill" />
<meta property="og:url" content="" />
<!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X630-->
<meta property="og:image" content="static/images/ico_2.png" />
<meta property="og:image:width" content="1200" />
<meta property="og:image:height" content="630" />


<meta name="twitter:title" content="CUA-Skill">
<meta name="twitter:description" content="A project homepage for CUA-Skill">
<!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X600-->
<meta name="twitter:image" content="static/images/ico_2.png">
<meta name="twitter:card" content="summary_large_image">
<!-- Keywords for your paper to be indexed by-->
<meta name="keywords" content="Application-Level Tool Selection Benchmark">
<meta name="viewport" content="width=device-width, initial-scale=1">


<title>CUA-Skill</title>
<link rel="icon" type="image/png" href="static/images/ico_2.png">
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">

<link rel="stylesheet" href="static/css/bulma.min.css">
<link rel="stylesheet" href="static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="static/css/bulma-slider.min.css">
<link rel="stylesheet" href="static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="static/css/index.css">

<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script src="https://documentcloud.adobe.com/view-sdk/main.js"></script>
<script defer src="static/js/fontawesome.all.min.js"></script>
<script src="static/js/bulma-carousel.min.js"></script>
<script src="static/js/bulma-slider.min.js"></script>
<script src="static/js/index.js"></script>
</head>

<body>


<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">CUA-Skill: Develop Skills for Computer Using Agent</h1>
<!-- <div class="is-size-5 publication-authors">
<span class="author-block">Tianyi Chen<sup>*</sup>,</span>
<span class="author-block">Michael Solodko<sup>*</sup>,</span>
<span class="author-block">Sen Wang,</span>
<span class="author-block">Jongwoo Ko,</span>
<span class="author-block">Junheng Hao,</span>
<span class="author-block">Colby Banbury,</span>
<span class="author-block">Sara Abdali,</span>
<span class="author-block">Saeed Amizadeh,</span>
<span class="author-block">Qing Xiao,</span>
<span class="author-block">Yinheng Li,</span>
<span class="author-block">Tianyu Ding,</span>
<span class="author-block">Kamran Ghasedi Dizaji,</span>
<span class="author-block">Suzhen Zheng,</span>
<span class="author-block">Hao Fan,</span>
<span class="author-block">Justin Wagle,</span>
<span class="author-block">Pashmina Cameron,</span>
<span class="author-block">Kazuhito Koishida</span>
</div>
<div class="is-size-6 has-text-grey">* Equal Contribution</div> -->

<div class="is-size-5 publication-authors">
<span class="author-block"><strong>Microsoft</strong> <br>January 2026</span>
<!-- <span class="eql-cntrb"><small><br><sup>*</sup>Indicates Equal Contribution</small></span> -->
</div>

<div class="column has-text-centered">
<div class="publication-links">
<!-- Github link -->
<span class="link-block">
<a href="https://github.com/microsoft/cua_skill" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>GitHub</span>
</a>
</span>

<!-- ArXiv abstract Link -->
<span class="link-block">
<a href="https://arxiv.org/abs/2511.19957" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>


<!-- Teaser video-->
<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<!-- <video poster="" id="tree" autoplay controls muted loop height="100%">
<source src="static/videos/banner_video.mp4" type="video/mp4">
</video> -->
<img src="static/images/cua_skill_results_plot.png" alt="" />
<!-- <h2 class="subtitle has-text-centered">
The AppSelectBench framework includes three core stages: (1) a multi-step generation pipeline producing over 100k realistic tasks; (2) a parallelized tool-selection core where multiple LLMs are tested against various protocols; and (3) the resulting in-depth performance analysis.
</h2> -->
</div>
</div>
</section>
<!-- End teaser video -->

<!-- Paper abstract -->
<section class="section hero is-light">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
Computer-Using Agents (CUAs) aim to autononomously operate computer systems to complete real-world desktop tasks. However, existing agentic systems remain difficult to scale and continue to lag behind human performance. A key limitation is the absence of reusable and structured skill abstractions that capture how humans interact with graphical user interfaces. We introduce CUA-Skill, a computer-using agentic skill base that encodes human computer-use knowledge as skills coupled with parameterized execution graphs. CUA-Skill is a large-scale library of carefully engineered skills spanning common Windows applications, serving as a practical infrastructure and tool substrate for scalable, reliable agent development. Built upon this skill base, we construct CUA-Skill Agent, an end-to-end computer-using agent that supports dynamic skill retrieval, argument instantiation, and memory-aware failure recovery. Our results demonstrate that CUA-Skill substantially improves execution success rates and robustness on challenging end-to-end agent benchmarks, establishing a strong foundation for future computer-using agent development. On WindowsAgentArena, CUA-Skill Agent achieves state-of-the-art 57.5% (best of three) successful rate while being significantly more efficient than prior and concurrent approaches.
</p>
</div>
</div>
</div>
</div>
</section>
<!-- End paper abstract -->

<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<h2 class="title is-3 has-text mt-5">Computer-Using Agentic Skills</h2>
<p class="has-text">
CUA-Skill consists of three components: (i) a skill cell that captures a minimal user intent, (ii) a parameterized execution graph that specifies concrete realizations of the skill through GUI-grounded interactions and executable scripts, and (iii) a skill composition graph that encodes how individual skills are typically chained together.
</p>
<div class="columns is-variable is-5 is-vcentered">
<div class="column">
<figure class="image">
<img src="static/images/cua_skill_and_graph_construction.png" alt="cua skill and graph construction" style="max-width: 80%; margin: 0 auto;" />
</figure>
</div>
<div class="column">
<figure class="image">
<img src="static/images/cua_skill_and_graph_construction_example.png" alt="cua skill and graph construction example" style="max-width: 90%; margin: 0 auto;" />
</figure>
</div>
</div>
</div>
</div>
</section>

<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<div class="columns is-variable is-3">
<div class="column is-8">
<h2 class="title is-3 has-text mt-5 mb-2">CUA-Skill Agent</h2>
<p class="has-text">
CUA-Skill Agent supports flexible, long-horizon task completion via dynamic skill selection and execution. Given a natural-language user instruction, the agent incrementally selects and executes skills from the CUA-Skill library, conditioning each decision on the current UI state, execution history, and accumulated memory. At each step, an LLM M𝑝 serves as the planner, determining both which skill to invoke next and how to instantiate its arguments
</p>
<figure class="image mt-4">
<img src="static/images/cua_skill_overview_v2.png" alt="cua skill overview" />
</figure>
</div>
<div class="column is-4">
<figure class="image mt-4">
<img src="static/images/cua_skill_agent.png" alt="cua skill agent" style="max-width: 80%; margin: 0 auto;" />
</figure>
</div>
</div>
</div>
</div>
</section>

<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<h2 class="title is-3 has-text mt-5">Experimental Results</h2>
<p>

Statistics of CUA-Skill Execution Graph across applications. The GUI primitive statistics measures per atomic skill, how the quantity of GUI primitives distributes. (Right) Bar plot of success rate across applications.
</p>
<div class="columns is-variable is-3 is-vcentered">
<div class="column">
<figure class="image">
<img src="static/images/atomic_skill_distribution.png" alt="Atomic skill distribution" style="max-width: 110%; margin: 0 auto;" />
</figure>
</div>
<div class="column">
<figure class="image">
<img src="static/images/accuracy_plot.png" alt="Accuracy plot" style="max-width: 70%; margin: 0 auto;" />
</figure>
</div>
</div>
<p class="mt-4">
Synthesized User Task Successful Rate. CUA-Skill is noticeablly higher than Ultra-CUA (Yang et al., 2025b) by 1.7x,<br />
and Operator by 3.64x.
</p>
<figure class="image">
<img src="static/images/synthesized_user_task_success_rate.png" alt="Synthesized user task successful rate" style="max-width: 70%; margin: 0 auto;" />
</figure>
<p class="mt-4">
Success Rate by Application Category of CUA-Skill Agent on WindowsAgentArena (Bonatti et al., 2024).
</p>
<figure class="image">
<img src="static/images/waa_success_rate.png" alt="WAA success rate by application category" style="max-width: 85%; margin: 0 auto;" />
</figure>
<p class="mt-4">Overall comparison of system performance on WAA</p>
<figure class="image">
<img src="static/images/other_method_performance.png" alt="Other method performance" style="max-width: 70%; margin: 0 auto;" />
</figure>
</div>
</div>
</section>





<!--BibTex citation -->
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>
@article{chen2025cuaskill,
title={CUA-Skill: Develop Skills for Computer Using Agent},
author={Chen, Tianyi and Li, Yinheng and Solodko, Michael and Wang, Sen and Jiang, Nan and Hao, Junheng and Cui, Tingyuan and Ko, Jongwoo and Abdali, Sara and Zheng, Suzhen and Fan, Hao and Cameron, Pashmina and Wagle, Justin and Koishida, Kazuhito}
journal={arXiv preprint arXiv:----},
year={2026}
}
</code></pre>
</div>
</section>
<!--End BibTex citation -->


<footer class="footer">
<div class="container">
<div class="columns is-centered">
<div class="column is-8">
<div class="content">

<p>
This page was built using the <a href="https://github.com/eliahuhorwitz/Academic-project-page-template"
target="_blank">Academic Project Page Template</a> which was adopted from the <a
href="https://nerfies.github.io" target="_blank">Nerfies</a> project page.
You are free to borrow the source code of this website, we just ask that you link back to this page in the
footer. <br> This website is licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/" target="_blank">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>

</div>
</div>
</div>
</div>
</footer>

<!-- Statcounter tracking code -->

<!-- You can add a tracker to track page visits by creating an account at statcounter.com -->

<!-- End of Statcounter Code -->

</body>

</html>
1 change: 1 addition & 0 deletions docs/static/css/bulma-carousel.min.css
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading