@inproceedings{zhang-etal-2025-vision-language,
    title = "Vision-and-Language Navigation with Analogical Textual Descriptions in {LLM}s",
    author = "Zhang, Yue  and
      Ma, Tianyi  and
      Wang, Zun  and
      Qiao, Yanyuan  and
      Kordjamshidi, Parisa",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.759/",
    pages = "15028--15036",
    ISBN = "979-8-89176-332-6",
    abstract = "Integrating large language models (LLMs) into embodied AI models is becoming increasingly prevalent. However, existing zero-shot LLM-based Vision-and-Language Navigation (VLN) agents either encode images as textual scene descriptions, potentially oversimplifying visual details, or process raw image inputs, which can fail to capture abstract semantics required for high-level reasoning. In this paper, we improve the navigation agent{'}s contextual understanding by incorporating textual descriptions that facilitate analogical reasoning across images from multiple perspectives. By leveraging text-based analogical reasoning, the agent enhances its global scene understanding and spatial reasoning, leading to more accurate action decisions. We evaluate our approach on the R2R dataset, where our experiments demonstrate significant improvements in navigation performance."
}