arXiv preprint / 评测基准

MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

作者：Ziyang Luo, Zhiqi Shen, Wenzhuo Yang, Zirui Zhao, Prathyusha Jwalapuram, Amrita Saha, Doyen Sahoo, Silvio Savarese, Caiming Xiong, Junnan Li · 单位：Salesforce AI Research, com/SalesforceAIResearch/MCP-Universe · 会议/期刊：arXiv preprint · 方向：评测基准 · 发布日期：2025-08-20

自我进化智能体评测基准大语言模型智能体模型自进化上下文演化
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers figure
AlphaXiv 中文概览（可滚动查看）