1
Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition
揭示LLM在调用陌生API时的知识短板，推出首个面向新型API获取能力的智能体评测基准。
arXiv:2606.03657v1 Announce Type: new Abstract: Large language models for code generation often need to use APIs that are absent from their pretrainin…