Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (22) · 18370-18378
DOI: 10.1609/aaai.v40i22.38901 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Pingrui Lai und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Vision-and-Language navigation on websites requires agents to navigate target webpages and answer questions based on human instructions. Current web agents primarily leverage Large Language Models (LLMs) for semantic understanding and reasoning, but still suffer from limited navigation performance and slow inference speed. Constructing a global map across webpages can effectively enhance both navigation accuracy and efficiency, however, this is challenged by the open structure of web navigation graphs and the dynamic nature of web layouts. In this paper, we propose ATLAS: Adaptive Topological Layout And Semantic mapping, a framework that adaptively constructs a time-varying, unbounded topological map across webpages and unifies heterogeneous elements through semantic representation. This enables both global path planning and local element selection for web-based navigation and question answering. As a lightweight approach, ATLAS significantly outperforms existing state-of-the-art methods on the WebVLN benchmark with a 10% improvement in success rate, and achieves the highest average task success rate on both the Mind2Web and WebArena benchmarks.
Zitieren
APA
Lai, P., Xie, Z., & Yang, H. (2026). Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites. Proceedings of the AAAI Conference on Artificial Intelligence, 40(22), 18370-18378. https://doi.org/10.1609/aaai.v40i22.38901
Vancouver
Lai P, Xie Z, Yang H. Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(22):18370-18378. doi:10.1609/aaai.v40i22.38901
BibTeX
@article{Lai2026,
author = {Lai, Pingrui and Xie, Zihao and Yang, Hua},
title = {Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {22},
pages = {18370--18378},
doi = {10.1609/aaai.v40i22.38901}
}
EUVIMED