Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA
LLM agents that interact with a user across many sessions accumulate histories that exceed their context window, so they store past interactions in an external memory and answer each question from a small set of retrieved records. Existing memory systems rank records by lexical or embedding relevance, yet the top-ranke...
Yufeng Li, Shu-Xin Li, Zhenhua Xu et al.
· 0 citations