Although vision-language navigation (VLN) has progressed rapidly, zero-shot VLN in continuous environments (VLN-CE) remains highly challenging when using lightweight vision-language models (VLMs), whose limited reasoning capacity makes long-horizon navigation unreliable. In this paper, we propose LightZeroNav to tackle the three major bottlenecks when using lightweight VLMs in zero-shot VLN-CE,i.e.,information redundancy from multi-source inputs, inaccurate progress estimation caused by noisy textual memory, and task entanglement between action execution and stage transition. Using only RGB observations and a lightweight open-source Qwen3-VL-8B backbone, LightZeroNav achieves competitive performance with GPT-4o (~200B) without task-specific training, graph search, or waypoint predictors, demonstrating its effectiveness in zero-shot VLN-CE.
@article{arxiv.2603.16947,
title = {LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs},
author = {Kun Luo and Xiangyu Dong and Xiaoguang Ma and Haoran Zhao and Yaoming Zhou},
journal= {arXiv preprint arXiv:2603.16947},
year = {2026}
}