@inproceedings{wang-etal-2026-synthagent,
    title = "{S}ynth{A}gent: Adapting Web Agents with Synthetic Supervision",
    author = "Wang, Zhaoyang  and
      Liang, Yiming  and
      Zhang, Xuchao  and
      Wu, Qianhui  and
      Han, Siwei  and
      Bastos, Anson  and
      Wang, Rujia  and
      Bansal, Chetan  and
      Peng, Baolin  and
      Gao, Jianfeng  and
      Rajmohan, Saravan  and
      Yao, Huaxiu",
    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.716/",
    pages = "15730--15752",
    ISBN = "979-8-89176-390-6",
    abstract = "Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues where synthesized tasks contain hallucinations that cannot be executed, and collected trajectories are noisy with redundant or misaligned actions. In this paper, we propose SynthAgent, a fully synthetic supervision framework that aims at improving synthetic data quality via dual refinement of both tasks and trajectories. Our approach begins by synthesizing diverse tasks through categorized exploration of web elements, ensuring efficient coverage of the target environment. During trajectory collection, tasks are refined only when conflicts with observations are detected, which mitigates hallucinations while preserving task consistency. After collection, we conduct trajectory refinement with global context to mitigate potential noise or misalignments. Finally, we fine-tune open-source web agents on the refined synthetic data to adapt them to the target environment. Experimental results demonstrate that SynthAgent outperforms existing synthetic data methods, validating the importance of high-quality synthetic supervision. The code is publicly available at https://github.com/aiming-lab/SynthAgent."
}