LycheeMemory V2 Consolidates Agent Memory at Semantic Segment Level, Not Per Turn: 92.20% on LongMemEval-S With 75.9% Fewer Construction Tokens

arXiv (via HuggingFace Daily Papers)·medium signalXBlueskyLinkedInCopy link

Submitted August 13 (arXiv 2608.12990) by Dongfang Li, Baotian Hu, Min Zhang and colleagues, LycheeMemory V2 replaces turn-level memory consolidation with semantic segment-level consolidation, using semantic boundary detection instead of fixed-window batching. It reports 89.22% on LoCoMo and 92.20% on LongMemEval-S while cutting construction tokens 86.0% and 75.9% respectively versus the A-Mem baseline. This is a different lever than last week's write-time-vs-retrieval framing: the win comes from how often you invoke the model to encode, which is the line item that actually shows up on an agent's bill.