René's URL Explorer Experiment


Title: Windows Agent Arena: Evaluating Multi-modal OS Agents at Scale

Description: Windows Agent Arena (WAA) is a scalable Windows AI agent platform for testing and benchmarking multi-modal, desktop AI agents. WAA provides researchers and developers with a reproducible and realistic Windows OS environment for AI research, where agentic AI workflows can be tested across a diverse range of tasks. WAA supports the deployment of agents at scale using the Azure ML cloud infrastructure, allowing for the parallel running of multiple agents and delivering quick benchmark results for hundreds of tasks in minutes, not days.

Keywords:

direct link

Domain: microsoft.github.io

Links:

Rogerio Bonattihttp://rogeriobonatti.com/
Dan Zhaohttps://www.linkedin.com/in/danzhao0/
Francesco Bonaccihttps://francescobonacci.com/
Sara Abdalihttps://www.microsoft.com/en-us/research/people/saraabdali/?msockid=25ed293ad143634b13e03b2dd00c62bf
Arthur Buckerhttps://arthurfenderbucker.github.io/
Lawrence Janghttps://lawrencekjang.github.io/
Paper https://microsoft.github.io/static/files/windows_agent_arena.pdf
arXiv https://arxiv.org/abs/2409.08264
Video https://microsoft.github.io/static/videos/waa_intro.mp4
Code https://github.com/microsoft/WindowsAgentArena
Blog post https://www.microsoft.com/applied-sciences/projects/windows-agent-arena
OSWorldhttps://os-world.github.io/
Tesseracthttps://github.com/tesseract-ocr/tesseract
Grounding DINOhttps://github.com/IDEA-Research/GroundingDINO
OmniParserhttps://arxiv.org/abs/2408.00203
https://microsoft.github.io/static/files/windows_agent_arena.pdf
https://github.com/microsoft/WindowsAgentArena
Creative Commons Attribution-ShareAlike 4.0 International Licensehttp://creativecommons.org/licenses/by-sa/4.0/
source codehttps://github.com/nerfies/nerfies.github.io

Viewport: width=device-width, initial-scale=1

URLs of crawlers that visited me.