Zhengxi Lu

Self-Distilled Agentic Reinforcement Learning

arXiv 2026

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

arXiv 2026

KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation

arXiv 2026

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

arXiv 2026

UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding

arXiv 2026

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning

arXiv 2026

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles

arXiv 2026

UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization

arXiv 2026

GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

arXiv 2025

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

arXiv 2025

UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning

arXiv 2025

MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

arXiv 2025

Mobile-Agent-v3: Fundamental Agents for GUI Automation

arXiv 2025

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

arXiv 2025

Weiming Lu

Yongliang Shen

Jun Xiao

Yueting Zhuang

Fei Tang

Guangyi Liu

Hao Wang

Jinyang Wu

Liang Liu

Wenqi Zhang