LinkedIn Paper Tests Memory Portability Across Models: Notes Swing ±10-13 Points, Knowledge Graphs Barely Move

dair_ai · x · 2026-09-07

A new LinkedIn paper tackles an overlooked question: can an agent's memory survive swapping the underlying model? The team stored the same agent history four ways—verbatim long context, chunked for retrieval, model-written notes, and a fixed-schema knowledge graph—then swapped the model doing the reading.

Results diverged sharply:

dair-ai calls memory one of the hardest things to get right when building agents and worth deliberate optimization. As users increasingly move between models, agents, and providers, memory portability is becoming a core engineering concern—especially for anyone who upgraded an agent's model only to watch it forget.

Original post →

More from coding & agent

coding & agent channel →