Envisioning Agentic Robotics: A New Era of Robotic Systems Paper • 2611.18359 • Published 7 days ago • 135
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop Paper • 2610.22740 • Published 29 days ago • 49
RoboHarness: A Simple Harness Outperforms VLA and World Action Models Paper • 2610.14018 • Published Oct 16 • 7
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Paper • 2606.31825 • Published Jun 30 • 24
TheCluster/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8 Image-Text-to-Text • 9B • Updated Apr 25 • 7.94k • 44