Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation 文章

ArXiv CS.AI2026-05-27NEWSen作者: Heng Qu, Yike Liu, Renren Jin, Wenzong Zhang, Pengzhi Gao, Wei Liu, Jian Luan

大语言模型

查看原文 →

Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation · 相关技术

相关技术

API ORM ODE language model 远程代码执行（RCE）reinforcement learning eval Unified Straight-Through Estimator SUL Vision-Language Models VLM HIS For Effort Metric Attention ARG ANN Agent