Unverified50% confidenceFactTime unknown
The LLM in Function Calling does not execute code directly, but generates structured descriptions of calling intent, decoupling decision-making from execution
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
Verified大模型执行Function Calling时本身并不真正执行调用，只输出意图声明，真正的执行由宿主应用完成79% similarVerifiedFunction Calling的原理是模型在推理时除了生成自然语言文本外，还能输出结构化的函数调用指令（包含函数名和参数的JSON）74% similarUnverifiedFunction Calling本质上是模型决策、外部执行的两阶段流程，模型本身并不直接运行代码73% similarUnverifiedFunction Calling采用关注点分离设计，语言模型只负责决策，真正的工具执行由应用层代码负责，模型不直接触碰外部系统72% similarUnverifiedFunction Calling 是指模型在生成响应时声明需要调用某个函数并传入特定参数，由外部系统执行后将结果返回给模型70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/54242API
curl https://kongchang.com/api/v1/knowledge/claims/54242MCP
get_claim(id=54242)