연구
HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance
arXiv:2602.23367v1 Announce Type: new Abstract: Model Context Protocol MCP servers contain a collection of thousands of opensource standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, humanlike user queries, remaining a critical gap in...
arXiv:2602.23367v1 Announce Type: new Abstract: Model Context Protocol MCP servers contain a collection of thousands of opensource standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, humanlike user queries, remaining a critical gap in evaluating the tool usage and ecosystems of MCP servers.
이 콘텐츠는 ArXiv AI 원본 기사의 요약입니다. 전문은 원본 사이트에서 확인해주세요.
원문 기사 보기 →