@article{activeo3empoweringmultimodallarge,
  title = {Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO},
  author = {Muzhi Zhu and Hao Zhong and Canyu Zhao and Zongze Du and Zheng Huang and MingYu Liu and Hao Chen and Cheng Zou and Jingdong Chen and Ming Yang and Chunhua Shen},
  year = {2025},
  eprint = {2505.21457},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.21457v1},
}