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

TL;DR

UI-Genie is a self-improving framework that enhances GUI agents by combining a reward model and iterative data generation, leading to state-of-the-art performance in mobile GUI tasks.

Contribution

The paper introduces UI-Genie, a novel self-improving approach with a new reward model and data generation pipeline for boosting MLLM-based GUI agents.

Findings

Achieves state-of-the-art results on multiple GUI benchmarks.

Generates high-quality synthetic trajectories without manual labeling.

Demonstrates effective self-improvement through iterative data-model enhancement.

Abstract

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.