@inproceedings{mo-etal-2026-navigating,
    title = "Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration",
    author = "Mo, Guozhao  and
      Liu, Yanjiang  and
      Shi, Yafei  and
      Chen, Jiawei  and
      Li, Yang  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      He, Ben  and
      Sun, Le  and
      Zheng, Bo  and
      Han, Xianpei",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.384/",
    pages = "8218--8232",
    ISBN = "979-8-89176-380-7",
    abstract = "Dynamic web navigation is challenging due to infinite decision space and the constantly changing nature of cyberspace. Existing methods rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models. In this paper, we propose HintNavigator, a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration (ICE). Inspired by the human cognitive planning process, we categorize the interaction history into Declarative History (environment observations) and Procedural History (action trajectories) to enhance historical reflection capability. These dual-history streams are dynamically integrated through specialized cognitive agents, enabling effective self-directed backtracking guided by working memory consolidation. Experiments show that HintNavigator achieves state-of-the-art performance among open-source LLM agents, surpassing proprietary model Claude-3.5 Sonnet on the WebArena benchmark."
}