Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents

arXiv:2609.03438 · cs.AI · Submitted 2026-09-03 · Read on arXiv

cs.AI

Submitted: 2026-09-03

Updated: 2026-09-03

Code: https://github.com/serein356/ConflictGuard

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

Terminology

• Steering — 44× in this paper · explained in 2 episodes
• Calibration — 32× in this paper · explained in 7 episodes
• Verification — 29× in this paper · explained in 2 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Grounding — 16× in this paper · explained in 3 episodes
• Success Rate — 10× in this paper
• Activation Steering — 9× in this paper · explained in 4 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Generalization — 5× in this paper · explained in 13 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Failure Modes — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Representation Engineering — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Activation Addition — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Sycophancy — 1× in this paper · explained in 4 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Understanding intermediate layers using linear classifier probes
• Refusal in Language Models Is Mediated by a Single Direction
• Qwen3-VL Technical Report
• Eliciting Latent Predictions from Transformers with the Tuned Lens
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Finding Neurons in a Haystack: Case Studies with Sparse Probing
• Faithful Mobile GUI Agents with Guided Advantage Estimator
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Kimi K2.5: Visual Agentic Intelligence
• UI-Venus-1.5 Technical Report
• Steering Language Models With Activation Engineering
• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
• The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
• Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models
• VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
• See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
• Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
• VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks
• Representation Engineering: A Top-Down Approach to AI Transparency

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