@inproceedings{wang-etal-2026-webclipper,
    title = "{W}eb{C}lipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning",
    author = "Wang, Junjie  and
      Xie, Zequn  and
      Yang, Dan  and
      Feng, Jie  and
      Shen, Yue  and
      Sun, Duolin  and
      Long, Meixiu  and
      Jiao, Yihan  and
      Tan, Zhehao  and
      Wang, Jian  and
      Wei, Peng  and
      Gu, Jinjie",
    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.988/",
    pages = "21646--21666",
    ISBN = "979-8-89176-390-6",
    abstract = "Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning. Concretely, we model the agent{'}s search process as a state graph and cast trajectory optimization as a minimum-necessary Directed Acyclic Graph (DAG) mining problem, yielding pruned trajectories that preserve essential reasoning while eliminating redundant steps. Continued training on these refined trajectories enables the agent to evolve toward more efficient search patterns and reduces tool-call rounds by about 20{\%} while improving accuracy. Furthermore, we introduce a new metric called F-AE Score to measure the model{'}s overall performance in balancing accuracy and efficiency. Experiments demonstrate that WebClipper compresses tool-call rounds under excellent performance, providing practical insight into balancing effectiveness and efficiency in web agent design."
}