This repository provides researchers with a comprehensive overview of RL-based reasoning MLLMs, compiling relevant projects and insights into this emerging field. It references notable systems such as DeepSeek-R1, Kimi k1.5, OpenAI o3-mini, and Grok 3 that demonstrate reasoning capabilities enhanced through reinforcement learning. The collection serves as a reference resource for tracking developments in large reasoning models within the multimodal AI research community.