Metraipolis › archive › dc_82cd4db9789f

GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments — arXiv:2609.00048

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00048
License (as archived): CC0-1.0
Archived: 2026-10-17T06:32:34.918Z
SHA-256 of the archived text: fc256a07f0da5f32142371d2fb16a12fbba3074159421ef8b314464b366ffec5
Stable URL of this page: https://metraipolis.com/documento/dc_82cd4db9789f

How to cite

GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments — arXiv:2609.00048 — arXiv (en), https://arxiv.org/abs/2609.00048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_82cd4db9789f (Metraipolis archive dc_82cd4db9789f, sha256 fc256a07f0da5f32142371d2fb16a12fbba3074159421ef8b314464b366ffec5)

BibTeX

@misc{dc82cd4db9789f,
  title = {GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments — arXiv:2609.00048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_82cd4db9789f; sha256 fc256a07f0da5f32142371d2fb16a12fbba3074159421ef8b314464b366ffec5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

GUI world models are increasingly evaluated as one-step next-screen predictors, yet their intended use is often as multi-step environments for GUI agents. This mismatch leaves a key requirement under-tested: generated states must remain contextually consistent when they are repeatedly reused for future interaction. We introduce GUI-CC, a benchmark that evaluates contextual consistency of GUI world models as agent environments rather than isolated next-screen predictors. GUI-CC contains two complementary tracks: an offline reference-action track that rolls models along real mobile GUI trajectories, and an online agent-loop track that lets fixed probing agents interact with model-generated UIs. We construct 500 offline trajectory tasks from GUIOdyssey and 200 emulator-verified online tasks across 30 mobile apps. GUI-CC evaluates transition fidelity, transition plausibility, contextual consistency, and task progress. Experiments show that plausible single-step generation does not guarantee reliable environment simulation: current models often produce usable-looking screens while failing to preserve task-relevant context or support executable multi-step rollouts.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00048 — 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 2026-10-17T06:15:12.713Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).