[논문리뷰] MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic EnvironmentsarXiv에 게시된 'MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments' 논문에 대한 자세한 리뷰입니다.#Review#Mobile GUI Agents#Memory Benchmarking#Short-Term Memory#Long-Term Memory#LLM-as-Judge#Dynamic Environments#Evaluation Metrics#Task Automation2026년 2월 8일댓글 수 로딩 중
[논문리뷰] OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic WorkflowsarXiv에 게시된 'OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows' 논문에 대한 자세한 리뷰입니다.#Review#Mobile GUI Agents#Agent Safety#Hybrid Detection#Formal Verification#VLM-based Contextual Judgment#Safety Benchmark#Risk Detection2025년 11월 9일댓글 수 로딩 중
[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI AgentsZhengxi Lu이 arXiv에 게시한 'MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents' 논문에 대한 자세한 리뷰입니다.#Review#Mobile GUI Agents#Hybrid Automation#Shortcut Generation#Benchmark#Task Efficiency#LLM-based Agents#Mobile Robotics2025년 9월 9일댓글 수 로딩 중