Advances in Neural Information Processing Systems 37 / 评测基准

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

作者：Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, Tao Yu · 单位：The University of Hong Kong, CMU, Salesforce Research, University of Waterloo · 会议/期刊：Advances in Neural Information Processing Systems 37 · 方向：评测基准 · 发布日期：2024-04-11

自我进化智能体评测基准进化算法
新标签打开 AlphaXiv
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments figure
AlphaXiv 中文概览（可滚动查看）