Skip to content

Source paper

Step-GUI Technical Report

Haolong Yan, Jia Wang, Xin Huang and 94 more

Haolong Yan, Jia Wang, Xin Huang, Yeqing Shen, Ziyang Meng, Zhimin Fan, Kaijun Tan, Jin Gao, Lieyu Shi, Mi Yang, Shiliang Yang, Zhirui Wang, Brian Li, Kang An, Chenyang Li, Lei Lei, Mengmeng Duan, Danxun Liang, Guodong Liu, Hang Cheng, Hao Wu, Jie Dong, Junhao Huang, Mei Chen, Renjie Yu, Shunshan Li, Xu Zhou, Yiting Dai, Yineng Deng, Yingdan Liang, Zelin Chen, Wen Sun, Chengxu Yan, Chunqin Xu, Dong Li, Fengqiong Xiao, Guanghao Fan, Guopeng Li, Guozhen Peng, Hongbing Li, Hang Li, Hongming Chen, Jingjing Xie, Jianyong Li, Jingyang Zhang, Jiaju Ren, Jiayu Yuan, Jianpeng Yin, Kai Cao, Liang Zhao, Liguo Tan, Liying Shi, Mengqiang Ren, Min Xu, Manjiao Liu, Mao Luo, Mingxin Wan, Na Wang, Nan Wu, Ning Wang, Peiyao Ma, Qingzhou Zhang, Qiao Wang, Qinlin Zeng, Qiong Gao, Qiongyao Li, Shangwu Zhong, Shuli Gao, Shaofan Liu, Shisi Gao, Shuang Luo, Xingbin Liu, Xiaojia Liu, Xiaojie Hou, Xin Liu, Xuanti Feng, Xuedan Cai, Xuan Wen, Xianwei Zhu, Xin Liang, Xin Liu, Xin Zhou, Yingxiu Zhao, Yukang Shi, Yunfang Xu, Yuqing Zeng, Yixun Zhang, Zejia Weng, Zhonghao Yan, Zhiguo Huang, Zhuoyu Wang, Zheng Ge, Jing Li, Yibo Zhu, Binxing Jiao, Xiangyu Zhang, Daxin Jiang

arXiv 2512.15431 · 2025118 upvotes on Hugging Face

Research ideas from this paper (4)

Generated by AI. The paper’s authors did not write these.

AI summary

The paper introduces Step-GUI, a family of multimodal models (4B/8B) specifically optimized for GUI automation through a self-evolving training pipeline. This pipeline uses a Calibrated Step Reward System (CSRS) to convert model-generated trajectories into high-quality training data at significantly lower costs while introducing GUI-MCP for secure, cross-platform deployment. Evaluation on the new AndroidDaily benchmark shows Step-GUI achieves state-of-the-art performance in real-world mobile and desktop scenarios.

How it works (AI summary)

The system utilizes a three-stage training paradigm (Mid-training, Cold-start, and RLVR) powered by the Calibrated Step Reward System (CSRS), which uses trajectory-level binary validation and LLM-based 'thinking models' to extract seven categories of dense reasoning data for iterative model refinement.