Unverified50% confidenceBenchmarkExact time
Official tests show that after integrating OpenViking, long-conversation memory accuracy for several agents exceeded 80%, and input token consumption was reduced.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedExperimental data indicate that vocabulary memorization efficiency combined with contextual cues can be improved by 40%–60%.69% similarUnverifiedIndustry estimates suggest that implicit tokens (system prompts, RAG retrieval context, function descriptions, and conversation history) typically account for 60%–80% of total consumption per request.65% similarUnverifiedOn dependency tasks, memory raised the success rate from a leakage-verified baseline of 0.00 to 0.55–1.00.65% similarUnverified研究显示复杂代理任务的token消耗往往是等效单次对话的20-100倍64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/912685API
curl https://kongchang.com/api/v1/knowledge/claims/912685MCP
get_claim(id=912685)