@article{tonguibuildinggeneralizedguiagentsby, title = {TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials}, author = {Bofei Zhang and Zirui Shang and Zhi Gao and Wang Zhang and Rui Xie and Xiaojian Ma and Tao Yuan and Xinxiao wu and Song-Chun Zhu and Qing Li}, year = {2025}, eprint = {2504.12679}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.12679v2}, }