[1]
Chen, S. et al. 2026. D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 21 (Mar. 2026), 17419–17426. DOI:https://doi.org/10.1609/aaai.v40i21.38795.