OpenPhone: Mobile Agentic Foundation Models

arXiv:2510.22009 · cs.AI · Submitted 2025-10-24 · Read on arXiv

cs.AI

Submitted: 2025-10-24

Updated: 2026-10-05

Code: https://github.com/HKUDS/PhoneCLI

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO — 1× in this paper · explained in 6 episodes

Sources

• OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
• WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
• AutoGLM: Autonomous Foundation Agents for GUIs
• Qwen2.5-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Proximal Policy Optimization Algorithms
• AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents
• GPT-4o System Card
• Qwen3-VL Technical Report
• MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents
• UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
• MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
• MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Small Language Models are the Future of Agentic AI

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems