Make memory an action space the agent navigates, not a blob you retrieve into it (NapMem)

arXiv 2607.05794·medium signal

NapMem (arXiv 2607.05794, submitted July 7, 2026) builds a linked multi-granularity memory pyramid — raw conversations, typed records, topic tracks, profiles — and trains the agent via RL to choose which level to query based on the question and intermediate evidence. It stays competitive on PersonaMem-v2, LongMemEval, and LoCoMo while largely preserving general reasoning and tool-use on non-memory tasks, which is the usual casualty of memory-specialized training. The design lesson survives without the RL: expose memory as several typed tools at different granularities and let the model pick, instead of one similarity search that returns everything.