Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning Paper • 2601.20209 • Published 6 days ago • 22
AgentDoG Collection A Diagnostic Guardrail Framework for AI Agent Safety and Security • 11 items • Updated 6 days ago • 87
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 12 days ago • 89
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models Paper • 2512.24618 • Published Dec 31, 2025 • 146