distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
Teams bolting memory onto agents usually assume more retrieved context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → is strictly better, and this shows accuracy and cost both turn on the dose and the delivery mode.
videoMemory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.aiAI Engineer
articleFilesystem-Based Memory for LLM Agents: Organization, Evolution, and SustainabilitySizhe Zhou, Sheldon Yu, Hui Wei, Junda Wu, Siru Ouyang, Yizhu Jiao, Shijia Pan, Julian McAuley, Yu Zhang, Tong Yu, Jiawei Han
postAI Agent Stack Everyone Must Use in 2026 (Builder’s Guide)Avid