Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments

arXiv:2608.24099 · cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/gguogan/AnTrap

Terminology

• Robustness — 41× in this paper · explained in 5 episodes
• Benchmark — 36× in this paper · explained in 2 episodes
• GRPO — 29× in this paper · explained in 6 episodes
• Grounding — 21× in this paper · explained in 3 episodes
• Hallucination — 10× in this paper · explained in 3 episodes
• Benchmarking — 6× in this paper · explained in 3 episodes
• Actor — 5× in this paper · explained in 3 episodes
• Action Space — 4× in this paper · explained in 1 episode
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Adversarial Training — 2× in this paper · explained in 1 episode
• Agentic System — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Affordance — 1× in this paper · explained in 1 episode
• Android Debug Bridge — 1× in this paper
• Commentary — 1× in this paper · explained in 2 episodes
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Set of Marks — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Vision-Language Model — 1× in this paper
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
• VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics
• When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
• MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments
• It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
• PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Android in the Wild: A Large-Scale Dataset for Android Device Control
• AmbiBench: Benchmarking Mobile GUI Agents Beyond One-Shot Instructions in the Wild
• Qwen3 Technical Report
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
• OpenComputer: Verifiable Software Worlds for Computer-Use Agents
• Step-level Optimization for Efficient Computer-use Agents
• GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
• BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism
• MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment
• OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
• OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
• Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
• Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents

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