Metraipolis › archive › dc_440c76d69a63

Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents — arXiv:2609.03438

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03438
License (as archived)
CC0-1.0
Archived
2026-10-17T01:10:34.586Z
SHA-256 of the archived text
c5a78fa9bf510dd1b9462f8c33458a89d030a94df50e568e2d453f9dfe50aa57
Stable URL of this page
https://metraipolis.com/documento/dc_440c76d69a63

How to cite

Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents — arXiv:2609.03438 — arXiv (en), https://arxiv.org/abs/2609.03438 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_440c76d69a63 (Metraipolis archive dc_440c76d69a63, sha256 c5a78fa9bf510dd1b9462f8c33458a89d030a94df50e568e2d453f9dfe50aa57)
BibTeX
@misc{dc440c76d69a63,
  title = {Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents — arXiv:2609.03438},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03438},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_440c76d69a63; sha256 c5a78fa9bf510dd1b9462f8c33458a89d030a94df50e568e2d453f9dfe50aa57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03438. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03438 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:28:02.847Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).