Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiao, Han, Wang, Guozhi, Chai, Yuxiang, Lu, Zimu, Lin, Weifeng, He, Hao, Fan, Lue, Bian, Liuyang, Hu, Rui, Liu, Liang, Ren, Shuai, Wen, Yafei, Chen, Xiaoxin, Zhou, Aojun, Li, Hongsheng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents
by: Xiao, Han, et al.
Published: (2026)

GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices
by: Lu, Xudong, et al.
Published: (2025)

AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents
by: Chai, Yuxiang, et al.
Published: (2024)

MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs
by: Lu, Zimu, et al.
Published: (2024)

LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
by: Liu, Guangyi, et al.
Published: (2025)

UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents
by: Chai, Yuxiang, et al.
Published: (2026)

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
by: Liu, Guangyi, et al.
Published: (2026)

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
by: Lu, Xudong, et al.
Published: (2024)

A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation
by: Chai, Yuxiang, et al.
Published: (2025)

UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
by: Lu, Zhengxi, et al.
Published: (2025)

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
by: Cheng, Pengzhou, et al.
Published: (2025)

UI-TARS: Pioneering Automated GUI Interaction with Native Agents
by: Qin, Yujia, et al.
Published: (2025)

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
by: Liu, Guangyi, et al.
Published: (2025)

UI-UG: A Unified MLLM for UI Understanding and Generation
by: Yang, Hao, et al.
Published: (2025)

ShowUI-Aloha: Human-Taught GUI Agent
by: Zhang, Yichun, et al.
Published: (2026)

MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
by: Lu, Zimu, et al.
Published: (2024)

PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
by: Chai, Yuxiang, et al.
Published: (2026)

Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
by: Lu, Zimu, et al.
Published: (2024)

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding
by: Xiao, Han, et al.
Published: (2025)

ShowUI: One Vision-Language-Action Model for GUI Visual Agent
by: Lin, Kevin Qinghong, et al.
Published: (2024)

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
by: Yang, Zhen, et al.
Published: (2025)

SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing
by: Jing, Hongyi, et al.
Published: (2025)

Improved GUI Grounding via Iterative Narrowing
by: Nguyen, Anthony
Published: (2024)

Probability-Consistent Preference Optimization for Enhanced LLM Reasoning
by: Yang, Yunqiao, et al.
Published: (2025)

MobileFlow: A Multimodal LLM For Mobile GUI Agent
by: Nong, Songqin, et al.
Published: (2024)

OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents
by: Cheng, Pengzhou, et al.
Published: (2025)

CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
by: Ma, Xinbei, et al.
Published: (2024)

TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
by: Zhang, Bofei, et al.
Published: (2025)

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
by: Wang, Haoming, et al.
Published: (2025)

Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
by: Li, Aiden Yiliu, et al.
Published: (2025)

Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks
by: Wu, Zongru, et al.
Published: (2025)

MLLM-Based UI2Code Automation Guided by UI Layout Information
by: Wu, Fan, et al.
Published: (2025)

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
by: Zhang, Shaojie, et al.
Published: (2025)

PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents
by: Liu, Zikang, et al.
Published: (2025)

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
by: Zhou, Hanzhang, et al.
Published: (2025)

NODI: Out-Of-Distribution Detection with Noise from Diffusion
by: Zhou, Jingqiu, et al.
Published: (2024)

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
by: You, Keen, et al.
Published: (2024)

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
by: Yang, Wenkui, et al.
Published: (2026)

UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding
by: Lian, Shuquan, et al.
Published: (2025)

Aria-UI: Visual Grounding for GUI Instructions
by: Yang, Yuhao, et al.
Published: (2024)