Unverified50% confidenceFactExact time
模型的工具调用能力来自专门的微调训练，而非通用语言模型的自然涌现
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
MCP与Skills有何区别？AI Agent架构分层详解
Related Claims
Unverified微调是指在已具备通用语言理解能力的基础模型之上，用特定领域的专业数据进行二次训练，使模型在保留通用能力的同时对特定任务表现出更高的专业精度79% similarUnverifiedThe Skills paradigm uses the large language model itself to simultaneously perform intent understanding, slot filling, and parameter structuring, achieving zero-shot intent routing without requiring additional training data.77% similarUnverified大模型本质上是token生成器，训练目标是生成看起来自然的文本，而非精确的数据结构77% similarUnverifiedRobotic foundation models are derived from the technical paradigm of large language models and vision-language models, enabling a single model to generalize across tasks and scenarios through pre-training on massive multimodal data.77% similarVerified大语言模型的预训练阶段本质上属于自监督学习，是一种特殊的非监督学习，模型通过预测下一个词来从海量文本中自动学习语言规律76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/517390API
curl https://kongchang.com/api/v1/knowledge/claims/517390MCP
get_claim(id=517390)