IBM measured agent memory as a dose, not a switch.

Three memory strategies across eight models from 30B to 745B on AppWorld's 585 multi-step tasks. Curated retrieval gave gpt-oss-120b +16.1 percentage points on goal completion for 5% more tokens. DeepSeek-V3.2 needed the full guideline set for +9.5pp at a 78% token cost. GLM-5 gained nothing at all. (Hugging Face) Strong models don't need your memory system, and weak models need the cheap version of it. That inverts how most memory products are priced and positioned.