Register and share your invite link to earn from video plays and referrals.

cv usk
@cv_usk
AI / Software Research Notes AI Agent, LLMOps, MLOps, Software Architecture æŠ•çšżăŻć€‹äșșăźæ„èŠ‹ă§ă™ă€‚
Joined May 2026
287 Following    473 Followers
TL;DR: Jetriever shifts agent memory retrieval from similarity to utility. It scores every stored memory with a decision model, so implicit connections get found. Jetriever: Shifting Agent Memory Retrieval from Similarity to Utility Key points ăƒ»đŸ„œ A "nut allergy" note matters for a macaron recipe request that never mentions nuts. Similarity search misses it ăƒ»đŸŽŻ Every memory gets a calibrated "will this help the answer" probability; the whole pool is ranked and the top k go to the answer model ăƒ»đŸ§  Uses Jev, a System One decision model with world knowledge and calibrated probabilities ăƒ»đŸ“ˆ On InMind-125 the gold exchange is ranked 1st 84.8% of the time, versus 0.8% for BM25 and 0.0% for MiniLM ăƒ»âœ… End-to-end accuracy is 76.0%, against 14.4% for the best published memory system ăƒ»đŸ’ž About $0.008 per query, but cost grows with the number of candidates On MAB (a 60-question sample only) it also rises from 44.3% to 55.4%. But evaluation centers on planted facts, and Jev is accessed through a commercial API. Scaling to large memory stores is the open problem. #AgentMemory# #Retrieval#
Show more