What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? Paper • 2611.06483 • Published 7 days ago • 39 • 6
Running Agents 1 Provael ASR Leaderboard 🦾 1 Attack-success rates for VLA policies, with benign controls
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories Paper • 2607.15330 • Published Jul 16 • 70 • 3
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation Paper • 2601.22153 • Published Jan 29 • 77 • 4
GigaBrain-0: A World Model-Powered Vision-Language-Action Model Paper • 2510.19430 • Published Oct 22, 2025 • 55 • 6