@article{mainvlamodelingabstractionofintentionand, title = {MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models}, author = {Zheyuan Zhou and Liang Du and Zixun Sun and Xiaoyu Zhou and Ruimin Ye and Qihao Chen and Yinda Chen and Lemiao Qiu}, year = {2026}, eprint = {2602.02212}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02212}, }