@inproceedings{he-etal-2026-branch,
    title = "Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory",
    author = "He, Shiqi  and
      Cui, Yue  and
      Ma, Xinyu  and
      Li, Yaliang  and
      Ding, Bolin  and
      Chowdhury, Mosharaf",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.838/",
    pages = "18407--18418",
    ISBN = "979-8-89176-390-6",
    abstract = "Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical embodied reasoning in open web environments. However, existing approaches remain limited in reasoning depth and efficiency: vanilla linear methods fail at multi-step reasoning and lack effective backtracking, while other search strategies are coarse-grained and computationally costly. We introduce \textit{Branch-and-Browse}, a fine-grained web agent framework that unifies structured reasoning-acting, contextual memory, and efficient execution. It (i) employs explicit subtask management with tree-structured exploration for controllable multi-branch reasoning, (ii) bootstraps exploration through efficient web state replay with background reasoning, and (iii) leverages a page action memory to share explored actions within and across sessions. On the WebArena benchmark, Branch-and-Browse achieves a task success rate of 35.8{\%} and reduces execution time by up to 40.4{\%} relative to state-of-the-art methods. These results demonstrate that Branch-and-Browse is a reliable and efficient framework for LLM-based web agents. Code is available at https://anonymous.4open.science/r/Branch{\_}and{\_}Browse/."
}