Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published Oct 8 • 41
ARM-Thinker Collection [CVPR2026] ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning • 2 items • Updated Oct 13 • 2
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction Paper • 2609.32353 • Published Sep 26 • 8