PyVision-RL: Forging Open Agentic Vision Models via RL
arXiv:2602.20739v1 Announce Type: new Abstract: Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn …
Shitian Zhao, Shaoheng Lin, Ming Li, Haoquan Zhang, Wenshuo Peng, Kaipeng Zhang, Chen Wei
조회수 31회