Frontier computer-use agents leak private information inappropriately in 67.9% of tested scenarios on average, with 11 of 15 failing more than half the cases.
arXiv preprint arXiv:2511.20766 , year =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
MobileGym introduces a lightweight browser-hosted mobile simulation platform with deterministic JSON-based judging, parallel rollouts, and a 416-task benchmark showing +12.8 pp gains and 95.1% sim-to-real retention.
A blind replay script matches frontier model performance on static CUA benchmarks due to non-principled environments and evaluation methods, prompting PRISM design principles and the DigiWorld benchmark with improved statistical aggregation.
VaseMuseum is a training-free multimodal agent that combines DeepResearch-style retrieval, source/response reliability control, and best-of-K reranking to improve citation validity and reduce hallucination for museum VQA on ancient Greek pottery.
citing papers explorer
-
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Frontier computer-use agents leak private information inappropriately in 67.9% of tested scenarios on average, with 11 of 15 failing more than half the cases.
-
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
MobileGym introduces a lightweight browser-hosted mobile simulation platform with deterministic JSON-based judging, parallel rollouts, and a 416-task benchmark showing +12.8 pp gains and 95.1% sim-to-real retention.
-
Computer Use at the Edge of the Statistical Precipice
A blind replay script matches frontier model performance on static CUA benchmarks due to non-principled environments and evaluation methods, prompting PRISM design principles and the DigiWorld benchmark with improved statistical aggregation.
-
VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery
VaseMuseum is a training-free multimodal agent that combines DeepResearch-style retrieval, source/response reliability control, and best-of-K reranking to improve citation validity and reduce hallucination for museum VQA on ancient Greek pottery.