AgentDoG Collection A Diagnostic Guardrail Framework for AI Agent Safety and Security • 11 items • Updated 2 days ago • 81
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 8 days ago • 89
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models Paper • 2512.24618 • Published about 1 month ago • 146
Running on CPU Upgrade Featured 2.94k The Smol Training Playbook 📚 2.94k The secrets to building world-class LLMs