# VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation Source: [VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation]() Collection index: [llms.txt]() Data updated: 2025-10-27T07:02:34.900Z Authors: Neel P. Bhatt, Yunhao Yang, Rohan Siva, Pranay Samineni, Daniel Milan, Zhangyang Wang, Ufuk Topcu Published: 2025-09-23T03:23:03.000Z ## Abstract Rapid adaptation in unseen environments is essential for scalable real-world autonomy, yet existing approaches rely on exhaustive exploration or rigid navigation policies that fail to generalize. We present VLN-Zero, a two-phase vision-language navigation framework that leverages vision-language models to efficiently construct symbolic scene graphs and enable zero-shot neurosymbolic navigation. In the exploration phase, structured prompts guide VLM-based search toward informative and diverse trajectories, yielding compact scene graph representations. In the deployment phase, a neurosymbolic planner reasons over the scene graph and environmental observations to generate executable plans, while a cache-enabled execution module accelerates adaptation by reusing previously computed task-location trajectories. By combining rapid exploration, symbolic reasoning, and cache-enabled execution, the proposed framework overcomes the computational inefficiency and poor generalization of prior vision-language navigation methods, enabling robust and scalable decision-making in unseen environments. VLN-Zero achieves 2x higher success rate compared to state-of-the-art zero-shot models, outperforms most fine-tuned baselines, and reaches goal locations in half the time with 55% fewer VLM calls on average compared to state-of-the-art models across diverse environments. Codebase, datasets, and videos for VLN-Zero are available at: https://vln-zero.github.io/. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Vision-and-Language Navigation on R2R-CE unseen continuous (val)](): Vision-and-Language Navigation; R2R-CE unseen continuous (val); SR: 42.4. - [Vision-Language Navigation on RxR-CE (val-unseen)](): Vision-Language Navigation; RxR-CE (val-unseen); SR: 30.8. - [Vision-Language Navigation on R2R-CE (val-unseen)](): Vision-Language Navigation; R2R-CE (val-unseen); Success Rate (SR): 42.4. ## Original sources and implementation [Original paper]() [PDF]()