UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

HanXiao, guozhi wang, Yuxiang Chai, Zimu Lu, Weifeng Lin, Hao He, Lue Fan, bian liuyang, HURUI, Liang Liu, Shuai Ren, yafei wen, Xiaoxin Chen, AJ.Zhou, Hongsheng LI

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents: 38 upvotes on Hugging Face Daily Papers, #12 of 76 papers on 2025-05-28. Day-by-day upvote history.

In this paper, we introduce UI-Genie, a self-improving framework addressing two key challenges in GUI agents: verification of trajectory outcome is challenging and high-quality training data are not scalable. These challenges are addressed by a reward model and a self-improving pipeline, respectively. The reward model, UI-Genie-RM, features an image-text interleaved architecture that efficiently pro- cesses historical context and unifies action-level and task-level rewards. To sup- port the training of UI-Genie-RM, we develop deliberately-designed data genera- tion strategies including rule-based verification, controlled trajectory corruption, and hard negative mining. To address the second challenge, a self-improvement pipeline progressively expands solvable complex GUI tasks by enhancing both the agent and reward models through reward-guided exploration and outcome verification in dynamic environments. For training the model, we generate UI- Genie-RM-517k and UI-Genie-Agent-16k, establishing the first reward-specific dataset for GUI agents while demonstrating high-quality synthetic trajectory gen- eration without manual annotation. Experimental results show that UI-Genie achieves state-of-the-art performance across multiple GUI agent benchmarks with three generations of data-model self-improvement. We open-source our complete framework implementation and generated datasets to facilitate further research in https://github.com/Euphoria16/UI-Genie.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.