Verified65% confidenceOpinionExact time
Prompt engineering and RAG address making large models answer questions well, while Agent addresses making large models proactively think and solve problems.
3
Sources
65%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Verified检索增强生成（RAG）通过基于真实知识库内容回答来解决大模型的幻觉问题75% similarUnverified解决大模型知识边界问题的两大技术方向是持续微调（Fine-tuning）和RAG（检索增强生成），LangChain主要服务于RAG73% similarUnverifiedIn scenarios with complex document structures, chunking strategies, embedding model selection, reranking, and hallucination detection are engineering problems that RAG must address.72% similarUnverifiedFor complex problems, tools hand off to an LLM Agent for analysis, typically following the ReAct (Reasoning + Acting) paradigm.72% similarUnverified微调适合教模型'如何做'，RAG 适合教模型'知道什么'70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/905958API
curl https://kongchang.com/api/v1/knowledge/claims/905958MCP
get_claim(id=905958)