@inproceedings{tang-etal-2026-lpo,
    title = "{LPO}: Towards Accurate {GUI} Agent Interaction via Location Preference Optimization",
    author = "Tang, Jiaqi  and
      Xia, Yu  and
      Wu, Yi-Feng  and
      Hu, Yuwei  and
      Yuhui, Chen  and
      Chen, Qing-Guo  and
      Xu, Xiaogang  and
      Wu, Xiangyu  and
      LU, Hao  and
      Ma, Yanqing  and
      Lu, Shiyin  and
      Chen, Qifeng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.718/",
    pages = "14617--14628",
    ISBN = "979-8-89176-395-1",
    abstract = "The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of supervised fine-tuning (SFT) methods in current GUI agents for achieving spatial localization, these methods face substantial challenges due to their limited capacity to accurately perceive positional data. Existing strategies, such as reinforcement learning, often fail to assess positional accuracy effectively, thereby restricting their utility. In response, we introduce Location Preference Optimization (LPO), a novel approach that leverages locational data to optimize interaction preferences. LPO uses information entropy to predict interaction positions by focusing on zones rich in information. Besides, we further introduce a dynamic location reward function based on physical distance, reflecting the varying importance of interaction positions. Supported by Group Relative Preference Optimization (GRPO), LPO facilitates an extensive exploration of GUI environments and significantly enhances interaction precision. Comprehensive experiments demonstrate LPO{'}s superior performance, achieving SOTA results across both offline benchmarks and real-world online evaluations."
}