@inproceedings{chen-etal-2026-mads,
    title = "{M}a{DS}: Long-Horizon {GUI} Automation via Synergizing Dual-Layer Memory and Multi-Round Debate",
    author = "Chen, Pengchen  and
      Chen, Shi  and
      Ye, Qiming  and
      Chen, Xinli  and
      Li, Xinran  and
      Xiang, Wei",
    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.1202/",
    pages = "26158--26180",
    ISBN = "979-8-89176-390-6",
    abstract = "Automating Graphical User Interface (GUI) operations with Multimodal Large Language Models (MLLMs) is promising but remains bottlenecked in real-world long-horizon settings. Key challenges include ensuring precise grounding across diverse interfaces and handling irreversible errors in extended workflows. Current methods often struggle to distinguish targets in low Signal-to-Noise Ratio (SNR) environments and lack sufficient pre-execution verification to prevent error accumulation. To address this, we propose the Memory-augmented Debate System (MaDS). Specifically, MaDS combines: (1) a Dual-Layer Memory Module that integrates universal interaction priors with scenario-specific operational experience to mitigate grounding hallucinations; and (2) Multi-Round Debate that performs pre-execution verification, while transforming execution failures into retrievable Negative Warnings to reduce repeated errors. Additionally, we introduce MaDS-Benchmark, a benchmark for long-horizon mobile GUI tasks with process-oriented evaluation. Experiments show that MaDS achieves a 90.23{\%} Task Success Rate on MaDS-Benchmark and strong performance on public benchmarks including AITW, AITZ, CAGUI, and GUIOdyssey."
}