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

arXiv: https://arxiv.org/abs/2607.15550 · HTML: https://mlsanity.com/paper/2607.15550/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in World model security and GUI agents, one of 11 directions in World models.
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- World models / [World model security and GUI agents](https://mlsanity.com/wm/world-model-security-and-gui-agents/)
- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 30 of 30)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge](https://mlsanity.com/paper/2507.04447/) (2025)
- [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [Discovering and Achieving Goals via World Models](https://mlsanity.com/paper/2110.09514/) (2021)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [AutoGLM: Autonomous Foundation Agents for GUIs](https://mlsanity.com/paper/2411.00820/) (2024)
- [PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages](https://mlsanity.com/paper/2504.04377/) (2025)
- [MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control](https://mlsanity.com/paper/2410.17520/) (2024)
- [ViMo: A Generative Visual GUI World Model for App Agents](https://mlsanity.com/paper/2504.13936/) (2025)
- [WebWorld: A Large-Scale World Model for Web Agent Training](https://mlsanity.com/paper/2602.14721/) (2026)
- [RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation](https://mlsanity.com/paper/2509.15212/) (2025)
- [SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs](https://mlsanity.com/paper/2509.20758/) (2025)
- [MobileDreamer: Generative Sketch World Model for GUI Agent](https://mlsanity.com/paper/2601.04035/) (2026)
- [VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verification](https://mlsanity.com/paper/2503.18492/) (2025)
- [WebGuard: Building a Generalizable Guardrail for Web Agents](https://mlsanity.com/paper/2507.14293/) (2025)
- [NeuralOS: Towards Simulating Operating Systems via Neural Generative Models](https://mlsanity.com/paper/2507.08800/) (2025)
- [MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning](https://mlsanity.com/paper/2508.03700/) (2025)
- [OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows](https://mlsanity.com/paper/2510.24411/) (2025)
- [MobileWorldBench: Towards Semantic World Modeling For Mobile Agents](https://mlsanity.com/paper/2512.14014/) (2025)
- [SafePred: A Predictive Guardrail for Computer-Using Agents via World Models](https://mlsanity.com/paper/2602.01725/) (2026)
- [SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration](https://mlsanity.com/paper/2602.02419/) (2026)
- [Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control](https://mlsanity.com/paper/2510.14388/) (2025)

## Built on by (most cited first, 3 of 3)

- [Scaling GUI Agents with Visual State Transitions](https://mlsanity.com/paper/2607.24112/) (2026)
- [Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces](https://mlsanity.com/paper/2609.34974/) (2026)
- [Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents](https://mlsanity.com/paper/2610.11942/) (2026)

## Abstract (arXiv)

Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks because a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks through pre-execution instruction-level screening and action-level risk assessment. Specifically, the action-level assessment analyzes agent-proposed actions within current GUI states, anticipating likely outcomes to identify risks before they are executed. To enable these capabilities, we construct a unified safety-augmented world model (SAWM) via multi-task learning, integrating semantic next-state prediction with safety risk assessment. Extensive experiments demonstrate that SeerGuard generalizes effectively across diverse mobile GUI agents. On Qwen3-VL-8B-Instruct, it increases the safety-utility score from 0.191 to 0.596 at ω=0.8 and reduces the risk-cost score from 0.347 to 0.135 at α=0.8. Further analyses on our SAWM validate the effectiveness of the instruction-level screening, alongside the capability of action risk assessment and next-state prediction.