Open Foundations for Compute-Use Agents
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
This paper introduces an open-source framework for computer-use agents, featuring a large-scale dataset (AgentNet), annotation infrastructure, and reflective reasoning pipelines. Its 32B model sets a new SOTA on OSWorld-Verified with 34.8% success, surpassing OpenAI’s GPT-4o, and all resources are released to advance open CUA research.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack