@article{naturalgaiaaverifiablebenchmarkandhierar, title = {NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks}, author = {Zihan Zheng and Tianle Cui and Taoran Wang and Fengtao Wang and Jiahui Pan and Lewei He and Qianglong Chen}, year = {2025}, eprint = {2508.01330}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.01330}, }