{"slug": "do-gui-agents-know-when-not-to-act-enabling-conflict-aware-termination-for-gui", "title": "Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents", "summary": "Researchers introduced CONFLICTGUI, a benchmark for evaluating GUI agents' ability to recognize infeasible instructions, and found severe execution-biased overcompliance where agents continue executing under conflicting instructions. They proposed CONFLICTGUARD, an inference-time framework that improves conflict task success rate across five agents while preserving normal performance.", "body_md": "arXiv:2609.03438v1 Announce Type: new\nAbstract: Graphical user interface (GUI) agents are increasingly used to execute natural-language instructions on user interfaces, yet real users may issue infeasible instructions due to benign mistakes. A reliable agent should not only know how to act, but also when not to act. In this work, we introduce CONFLICTGUI, a benchmark covering instruction-internal conflicts and instruction-GUI context conflicts to study conflict-aware termination. Our evaluation reveals severe execution-biased overcompliance: agents that perform well on feasible tasks often continue to execute blindly under conflicting instructions. To mitigate this behavior, we propose CONFLICTGUARD, an inference-time framework that aligns an agent's feasibility awareness with its action generation. CONFLICTGUARD contains two coupled components: a feasibility verification protocol that guides the agent to assess instruction logic and GUI-side evidence before acting, and a conditional action modulation mechanism that steers agents from over-compliant execution into termination-oriented behavior. Experiments across five widely-used agents demonstrate that CONFLICTGUARD improves average conflict task success rate significantly, while preserving normal GUI-task performance. These results validate that a lightweight inference-time intervention can substantially boost GUI Agent's competence to identify inappropriate execution scenarios and refrain from unnecessary actions.", "url": "https://wpnews.pro/news/do-gui-agents-know-when-not-to-act-enabling-conflict-aware-termination-for-gui", "canonical_source": "https://arxiv.org/abs/2609.03438", "published_at": "2026-09-04 04:00:00+00:00", "updated_at": "2026-09-04 04:23:59.888478+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research"], "entities": ["CONFLICTGUI", "CONFLICTGUARD"], "alternates": {"html": "https://wpnews.pro/news/do-gui-agents-know-when-not-to-act-enabling-conflict-aware-termination-for-gui", "markdown": "https://wpnews.pro/news/do-gui-agents-know-when-not-to-act-enabling-conflict-aware-termination-for-gui.md", "text": "https://wpnews.pro/news/do-gui-agents-know-when-not-to-act-enabling-conflict-aware-termination-for-gui.txt", "jsonld": "https://wpnews.pro/news/do-gui-agents-know-when-not-to-act-enabling-conflict-aware-termination-for-gui.jsonld"}}