Unverified95% confidenceFactTime unknown
对话缓冲记忆（Buffer Memory）的token消耗随对话长度线性增长，信息保留度为100%
1
Sources
95%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAn agent's memory includes short-term memory (conversational context window, typically 4K–128K tokens), long-term memory (vector database), and procedural memory (intermediate state cache for tool calls).64% similarUnverifiedTraditional KV cache implementations pre-allocate contiguous GPU memory blocks of maximum length, resulting in an average of 60%–80% of pre-allocated memory being wasted.64% similarUnverifiedPagedAttention improves KV Cache memory utilization from below 40% to close to 100%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16087API
curl https://kongchang.com/api/v1/knowledge/claims/16087MCP
get_claim(id=16087)