1
To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
arXiv最新研究提出评估与优化LLM工具调用的通用框架，为模型何时该调用外部工具提供决策依据
arXiv:2605.00737v2 Announce Type: replace Abstract: Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However,…