Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization Paper • 2512.24615 • Published 5 days ago • 67
SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents Paper • 2512.22322 • Published 10 days ago • 37
Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning Paper • 2509.22601 • Published Sep 26, 2025 • 29