This page may contain stale information. Last updated: 2026-08-02
Definition
Agentic retrieval is the pattern where AI agents use embedding-based search (and often multi-hop / tool loops) to fetch evidence for reasoning, coding, or long-horizon tasks — beyond single-shot RAG.
Key Points
- Embedding quality directly affects which passages an agent ever sees
- Stronger embeddings can reduce downstream token spend in search-agent stacks (NVIDIA claims with nemotron-3-ultra search agent)
- Typical workloads: enterprise RAG, code retrieval, agent memory over long conversations
- 2026-10-12: pensieve — local hybrid semantic/exact search over repos and agent sessions via mcp (pensieve-local-indexing-ai-agents)
Related
Sources
Jul 2026: modus context-warehouse seed frames selective context composition as alternative to over-retrieval (2026-08-02-tnw-modus-10m-seed).