#retrieval

• 10 Sept 2026 · Study

  Agentic AI · Agent memory

  Short-term memory (the conversation in the context window) versus long-term memory (facts stored outside and retrieved when relevant), with a small long-term store built on embeddings.

• 25 Mar 2026 · Study

  LLMs · Embeddings

  Sentence embeddings for semantic search: mean-pooling a small encoder (all-MiniLM-L6-v2), cosine similarity, and finding the most relevant sentence for a query without any shared keywords.

• 25 Nov 2025 · Paper summary

  Paper summary: General Agentic Memory Via Deep Research

  General Agentic Memory keeps a light memory plus the full history in a page-store, then uses a "researcher" agent to build the right context at request time, like just-in-time compilation for memory.

• 4 Sept 2025 · AI updates

  EmbeddingGemma: a 308M multilingual embedding model for devices

  Google released EmbeddingGemma, a 308M-parameter embedding model with a 2K context supporting 100+ languages; at release it was the top text-only multilingual model under 500M on MTEB.