GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Paper • 2602.22190 • Published 12 days ago • 15
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency Paper • 2602.16745 • Published 20 days ago • 8
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning Paper • 2602.10090 • Published 27 days ago • 51
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning Paper • 2602.10090 • Published 27 days ago • 51
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Paper • 2602.08234 • Published 29 days ago • 69