The field of multimodal learning and agentic reinforcement learning is rapidly evolving, with a focus on developing models that can effectively interact with and utilize various tools and environments. Recent research has explored the use of reinforcement learning to enhance the capabilities of large language models, including their ability to reason and make decisions in complex, dynamic worlds. A key direction in this field is the development of unified models that can excel at both evaluation and generation tasks, such as the use of critic models as policy models. Another important area of research is the development of frameworks and platforms that can support the integration of multiple tools and modalities, enabling more efficient and effective learning and decision-making. Notable papers in this area include LLaVA-Critic-R1, which demonstrates the potential of critic models as competitive policy models, and VerlTool, which provides a unified and modular framework for agentic reinforcement learning with tool use. ReVPT also shows promising results in enhancing multi-modal LLMs' abilities to reason about and use visual tools through reinforcement learning. Overall, these advances have the potential to enable the development of more scalable, general-purpose AI agents that can effectively interact with and utilize various tools and environments.