Unverified50% confidenceFactExact time
普通大模型的工具调用是被动的，模型只能声明想调用某个函数及其参数，实际执行仍需外部系统完成
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
Unverified在纯Agent场景下，模型的指令遵循能力往往比参数量更重要76% similarUnverifiedA single function-calling process requires at least two large model invocations—one to decide which tool to call, and one to interpret the result returned by the tool.75% similarUnverifiedThe auxiliary model serves only as a front-end acceleration tool and does not replace the main model in core decision-making; the main model's original response style, semantic logic, and knowledge accuracy remain in their native state.75% similarUnverified控制流优先架构的核心思想是把大模型当作函数调用，用代码定义状态机、循环和错误处理，Prompt只负责单一明确的任务74% similarUnverifiedSkills 机制通过上下文注入在不修改模型权重的前提下引导模型输出，相比一次性 Prompt Engineering 强调可复用性、版本管理和模块化组合72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/571312API
curl https://kongchang.com/api/v1/knowledge/claims/571312MCP
get_claim(id=571312)