@inproceedings{fang-etal-2025-webevolver,
    title = "{W}eb{E}volver: Enhancing Web Agent Self-Improvement with Co-evolving World Model",
    author = "Fang, Tianqing  and
      Zhang, Hongming  and
      Zhang, Zhisong  and
      Ma, Kaixin  and
      Yu, Wenhao  and
      Mi, Haitao  and
      Yu, Dong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.454/",
    pages = "8970--8986",
    ISBN = "979-8-89176-332-6",
    abstract = "Agent self-improvement, where agents autonomously train their underlying Large Language Model (LLM) on self-sampled trajectories, shows promising results but often stagnates in web environments due to limited exploration and under-utilization of pretrained web knowledge. To improve the performance of self-improvement, we propose a novel framework that introduces a co-evolving World Model LLM. This world model predicts the next observation based on the current observation and action within the web environment. The World Model serves dual roles: (1) as a virtual web server generating self-instructed training data to continuously refine the agent{'}s policy, and (2) as an imagination engine during inference, enabling look-ahead simulation to guide action selection for the agent LLM. Experiments in real-world web environments (Mind2Web-Live, WebVoyager, and GAIA-web) show a 10{\%} performance gain over existing self-evolving agents, demonstrating the efficacy and generalizability of our approach, without using any distillation from more powerful close-sourced models."
}