@inproceedings{zhang-etal-2026-dont-act,
    title = "Don{'}t Act Blindly: Robust {GUI} Automation via Action-Effect Verification and Self-Correction",
    author = "Zhang, Yuzhe  and
      Xue, Xianwei  and
      Wu, Xingyong  and
      Chen, Mengke  and
      Liu, Chen  and
      He, Xinran  and
      Shao, Run  and
      Liu, Feiran  and
      Xu, Huanmin  and
      Pan, Qiutong  and
      Wang, Haiwei",
    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.1335/",
    pages = "28924--28941",
    ISBN = "979-8-89176-390-6",
    abstract = "Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency, rendering delays, and system interruptions, this assumption leads to undetected action failures, repetitive ineffective behaviors, and catastrophic error accumulation. Moreover, learning robust recovery strategies is challenging due to the high cost of online interaction and the lack of real-time feedback in offline datasets.We propose VeriGUI (Verification-driven GUI Agent), which explicitly models action outcomes and recovery under noisy environments. VeriGUI introduces a Thinking{--}Verification{--}Action{--}Expectation (TVAE) framework to detect failures and guide corrective reasoning, and a two-stage training pipeline that combines Robust SFT with synthetic failure trajectories and GRPO with asymmetric verification rewards. We further construct a Robustness Benchmark based on AndroidControl to evaluate failure recognition and correction. Experiments show that VeriGUI significantly reduces failure loops and improves recovery success while maintaining competitive standard task performance."
}