First Workshop on Computer Use Agents

We invite submissions addressing research questions and challenges in the development and deployment of agents designed to interact with and perform tasks on computer systems.

Beyond standard ML papers, we also encourage research that highlights engineering, safety and examines wider societal implications.

Accepted papers will be presented as posters during our poster sessions and selected papers will be presented as spotlight talks throughout the day.

✉️ submission tracks

• Paper Track with up to 8 pages (excluding references and supplementary materials).  Authors may optionally include a short video demonstration as supplementary material, however the focus should be on the paper.

• Demo Track with a video (max 20 minutes) showing the system in action, and an accompanying write-up of up to 2 pages (excluding references). Ideal for hands-on system demonstrations, novel software tools, or interactive proofs-of-concept.

Accepted demos will be invited to give an interactive demonstration during the poster session.

📚 scope of submissions

We encourage a broad range of submissions, including but not limited to:

• Learning Algorithms - which new architectures and learning techniques (e.g. memory mechanisms for extended tasks, exploration strategies) can enhance the intrinsic ability of computer use agents to acquire, represent, and refine knowledge?

• Orchestration - what novel frameworks or control methods (e.g. dynamic task planning, modular coordination, multi-agent systems) can efficiently manage and integrate multiple learning components to optimize overall agent performance?

• Interfaces - how should agents perceive and act within their environments (e.g., via APIs or UI interactions), and should we design unified systems or specialized agents for different modalities?

• Guardrails, safety & societal implications - what guardrails do we need in order to make computer use models safe for deployment ``in the wild'' while ensuring that they have a positive impact on society?

• Benchmarking & tools - how can we develop robust environments and evaluation metrics that capture the diversity of real-world settings? Do we need new tools or frameworks to make research on computer use more efficient and accessible?

• Human-agent interaction - how will future interactions evolve? Should we optimize agents for full autonomy or design them as personalized, human-centric collaborators?

• Broader applications - what are some practical applications for computer use agents across domains such as healthcare, scientific research, software engineering and testing etc.?

• Capability horizon - what breakthroughs or engineering challenges are required to enable agents orders of magnitude more capable than today, and what implications would such advances have?

🌱 miscellaneous

• Format: All submissions should follow the ICML 2025 style guidelines.

• Double-blind reviewing: please ensure you do not include any identifying information in your submission.

• Submissions must be made via OpenReview.

• We accept concurrent submissions (i.e., work under review elsewhere) and encourage authors to submit works-in-progress.

• Openness and reproducibility: Submissions featuring open-source code, detailed experimental sections and performance benchmarks are highly preferred.

🗓️ key dates

• Paper Submission Open

• Paper Submission Deadline: May 18, 2025*

• Acceptance Notification:  June 9, 2025

• Camera-Ready Deadline: June 30, 2025*

• Workshop Date: July 18, 2025 

* All dates have deadlines 11:59 pm AoE (Anywhere on Earth)

📣 become a Reviewer

We invite researchers, students, and industry experts to join our reviewer pool! If you are interested in contributing to the workshop by reviewing submissions, please fill out this form. We appreciate your support in maintaining a high-quality review process.

🗓️ contact

For any questions related to the workshop, submissions, or logistics, please reach out to the organizing committee at: wcua-icml-2025@googlegroups.com