PhoneCLI: From App Interfaces to Callable Commands for Mobile Agents
cs.AI
Submitted: 2026-09-28
Updated: 2026-10-05
Code: https://github.com/HKUDS/PhoneCLI
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- AutoGLM: Autonomous Foundation Agents for GUIs
- MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
- Large Language Model-Brained GUI Agents: A Survey
- MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
- PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions
- Generalization in Online Reinforcement Learning for Mobile Agents
- CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications
- Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
- PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
- UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents
- Kimi K3: Open Frontier Intelligence
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- GPT-4o System Card
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
- LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
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