Verified65% confidenceFactTime unknown
Conversational summary memory compresses historical interactions into a summary via an LLM, and the summary is iteratively updated whenever a new message is added.
3
Sources
65%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified短期记忆的管理策略包括消息截断（只保留最近N轮对话）和摘要压缩（用LLM将早期对话压缩成摘要）78% similarVerifiedContext compaction is a class of techniques that distill existing conversation history into a more concise representation, typically by having the model generate a summary of earlier content to replace the original message list.78% similarUnverifiedSummarization middleware is commonly used to compress long conversation histories or large documents in order to fit content within a model's limited context window.75% similarVerifiedThe context window refers to the length of text a model can remember and reference in a single conversation; information beyond this range is truncated and discarded.73% similarVerifiedConversational memory is stored in the form of memory summaries, which can become skewed as conversations grow, whereas global personalization instructions are hard-coded into the system prompt of every request and are not affected by memory degradation.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16088API
curl https://kongchang.com/api/v1/knowledge/claims/16088MCP
get_claim(id=16088)