Verified65% confidenceFactTime unknown
The memory of LLMs depends on the context window, which is the maximum number of tokens the model can process in a single inference.
3
Sources
65%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
吴恩达新课解读：Agent记忆工程从入门到实战
bilibili吴恩达Agents
Related Entities
Related Claims
UnverifiedLLM本质上是无状态的推理引擎，每次调用模型时所有记忆都必须以文本形式塞入上下文窗口80% similarVerifiedThe context window of a large language model determines the upper limit of information the model can process in a single inference.77% similarUnverifiedDuring LLM training, memorization occurs, where models may verbatim store fragments of training data and reproduce them during inference.77% similarUnverified上下文复用与内存管理是控制LLM推理成本的关键杠杆76% similarUnverifiedLLM自回归解码阶段每生成一个token都需从显存加载全量模型权重，批量较小时形成内存墙76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/17754API
curl https://kongchang.com/api/v1/knowledge/claims/17754MCP
get_claim(id=17754)