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

Every time a coding assistant loses track of a debugging thread, or a data analysis agent re-ingests the same context it already processed, the team pays in latency, token costs, and brittle workflows. The fix most teams reach for — expanding the context window or adding more RAG — is increasingly expensive and still doesn't reliably work. To address this, researchers from Mind Lab and several universities proposed delta-mem , an efficient technique that compresses the model’s