The field of vision-and-language navigation is moving towards more efficient and effective methods for navigating unknown environments. Researchers are focusing on developing frameworks that can integrate spatial layout priors and dynamic task feedback to improve navigation fidelity. Another key direction is the development of end-to-end zero-shot navigation methods that eliminate the need for panoramic views and waypoint predictors, enabling more practical and real-world applicable solutions. Noteworthy papers in this area include: NaviTrace, which introduces a high-quality Visual Question Answering benchmark for evaluating vision-language models' navigation capabilities. STRIDER, which proposes a novel framework that optimizes the agent's decision space by integrating spatial layout priors and dynamic task feedback. Fast-SmartWay, which presents an end-to-end zero-shot vision-and-language navigation framework that eliminates the need for panoramic views and waypoint predictors. Floor Plan-Guided Visual Navigation, which proposes a novel diffusion-based policy that integrates global path planning from the floor plan with local depth-aware features derived from RGB observations. MacroNav, which presents a learning-based navigation framework featuring a lightweight context encoder trained via multi-task self-supervised learning and a reinforcement learning policy that seamlessly integrates these representations with graph-based reasoning.