When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
A pre-registered study on held-out LoCoMo conversations and LongMemEval finds Jev selects as accurately as an LLM reranker at a third of the latency, and more accurately than a multi-call graph traversal.
Rishabh Sharma, Rishika Lall
· 1 citation