MeMo's memory model lets teams upgrade their LLM without retraining it — and performance jumps 26%

Researchers' MeMo keeps AI memory separate from reasoning, so teams can upgrade their LLM without retraining it and see a 26% ...

A 0.12% parameter add-on gives AI agents the working memory RAG can't

Researchers built delta-mem to give AI agents working memory at 0.12% parameter overhead, outperforming RAG and context ...