SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction

arXiv:2607.15550 · cs.AI · Submitted 2026-07-17 · Read on arXiv

cs.AI

Submitted: 2026-07-17

Updated: 2026-09-02

Comments: 19 pages, 8 figures

Project page: https://seerguard.github.io

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

Terminology

• World Model — 54× in this paper · explained in 7 episodes
• Alignment — 9× in this paper · explained in 1 episode
• F1 Score — 9× in this paper · explained in 3 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Core — 6× in this paper · explained in 2 episodes
• Risk-Cost Score — 6× in this paper
• Safety-Augmented World Model — 6× in this paper
• Safety-Utility Score — 6× in this paper
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Action Space — 4× in this paper · explained in 1 episode
• Ablation — 3× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Supervised Fine-Tuning — 2× in this paper
• Agentic AI — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Contextual Awareness — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Predictive Modeling — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• MobileDreamer: Generative Sketch World Model for GUI Agent
• Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
• RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
• Constitutional AI: Harmlessness from AI Feedback
• MobileWorldBench: Towards Semantic World Modeling For Mobile Agents
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
• SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
• MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning
• AutoGLM: Autonomous Foundation Agents for GUIs
• Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control
• WebWorld: A Large-Scale World Model for Web Agent Training
• Qwen3-VL Technical Report
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Agent-SafetyBench: Evaluating the Safety of LLM Agents
• WebGuard: Building a Generalizable Guardrail for Web Agents
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection