@article{evolvingintasksempoweringthemultimodalit, title = {Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent}, author = {Yuhao Cheng and Liang Tang and Shuxian Li and Yukang Huo and Tiaonan Duan and Kaer Huang and Yanzhe Jing and Yiqiang Yan}, year = {2025}, eprint = {2508.04037}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04037}, }