@misc{zhao2025mmhelix,
title = {MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization},
author = {Xiangyu Zhao and Junming Lin and Tian Liang and Yifan Zhou and Wenhao Chai and Yuzhe Gu and Weiyun Wang and Kai Chen and G. Luo and Wenwei Zhang and Junchi Yan and Hua Yang and Haodong Duan and Xue Yang},
year = {2025},
eprint = {2510.08540},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2510.08540},
}