RAG, Fine-Tuning & ContextYi Yu et al.
Agentic Memory
Published "Agentic Memory" — exposes storing, retrieving, updating, summarizing and discarding as tool calls, and trains them with step-wise reinforcement learning
Why it matters
A case in which what to remember and what to discard is learned rather than decided by people
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2601.01885Added in Week 35, 2026 · See that week