Unverified50% confidenceBenchmarkExact time
Long-term memory evaluation benchmarks (such as LongMemEval and the MemGPT benchmark) assess five dimensions: single-hop information extraction, cross-session reasoning, knowledge updating, temporal reasoning, and abstention judgment.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/22/2026
First Seen
Valid until: 12/21/2026
Sources
Related Entities
Related Claims
UnverifiedMemGAS is evaluated on four long-term memory benchmarks: Locomo, LongMemEval-S, LongMemEval-M, and LongMTBench Plus.76% similarUnverifiedConversational recall benchmarks such as LoCoMo and LongMemEval measure question-answering ability over conversation history, rather than whether memory has changed the actual behavior of tool-using agents.75% similarUnverifiedMemory conflict resolution involves a composite strategy of timestamp priority and confidence scoring.74% similarUnverified记忆增强型智能体通过持续读取用户历史交互数据来识别高频关注点，技术实现通常需对原始对话数据做向量化处理再通过相似度检索或关键词抽取筛选73% similarUnverifiedThe memory retrieval of Generative Agents extracts key memories based on importance, recency, and relevance scores.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/941823API
curl https://kongchang.com/api/v1/knowledge/claims/941823MCP
get_claim(id=941823)