The field of embodied navigation is witnessing significant advancements, with a focus on developing more robust and adaptable navigation systems. Researchers are exploring the integration of multimodal inputs, such as vision and language, to improve navigation performance in complex and dynamic environments. The use of large vision-language models and hierarchical reasoning architectures is becoming increasingly popular, enabling agents to better understand and interpret their surroundings. Additionally, there is a growing interest in developing generalist navigation agents that can follow free-form instructions and adapt to various environments and tasks. Notable papers include: MR.NAVI, which presents a mixed-reality navigation system for the visually impaired, and Astra, which proposes a comprehensive dual-model architecture for mobile robot navigation. Also, OctoNav-R1 achieves superior performance in generalist embodied navigation by leveraging a hybrid training paradigm and thinking-before-action approach.