OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools
cs.SE, cs.CL, cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
- OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
- Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
- MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion
- ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
- Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions
- ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis
- AutoGLM: Autonomous Foundation Agents for GUIs
- PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents
- AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications
- OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
- HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents
- UI-Venus-2 Technical Report
- UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
- Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
- MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
- Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties