ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Paper • 2609.40253 • Published • 8
miaoyanrui
xiamoent
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning new activity about 2 months ago
xiamoent/Agent-G2-ALFWorld-Webshop-sft-data:Update Agent-G2 citationOrganizations
None yet