Xiangyu Zhao Junming Lin Tianhao Liang Yifan Zhou Wenhao Chai Yuzhe Gu Weiyun Wang Kai Chen 0026 Gen Luo Wenwei Zhang Junchi Yan Hua Yang 0001 Haodong Duan Xue Yang 0005 MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization. 2025 October abs/2510.08540 CoRR https://doi.org/10.48550/arXiv.2510.08540 db/journals/corr/corr2510.html#abs-2510-08540 streams/journals/corr