Agentic and Advanced RAG Patterns
Parent: AI Agent Ecosystems · researched 2026-06-01T02:26:22.052Z· 28 sources · 8 concepts · skill ai-agent-engineering
AI & agent-engineering family ROUTER. Split into: ai-agents-orchestration (agent frameworks, multi-agent, memory, planning, guardrails, coding/GUI agents, autonomous loops, eval); ai-rag-retrieval (RA
ai-agent-engineering
- AI & agent-engineering family ROUTER. Split into: ai-agents-orchestration (agent frameworks, multi-agent, memory, planning, guardrails, coding/GUI agents, autonomous loops, eval); ai-rag-retrieval (RAG, iterative retrieval, vector/graph datastores); ai-llm-model-layer (training, fine-tuning, alignment/RLHF, compression, inference serving, transformer/multimodal architecture, model selection, observability); ai-mcp-sdk-prompting (MCP servers/builder, Anthropic SDK, prompt engineering, context engineering, LLM frameworks, tool-search, prompt lookup). Route to the matching sub-hub. [source]
- This hub routes to on-demand reference files under references/. See each spoke for depth. [source]
Children
- Naive-RAG failure taxonomy (Barnett 7 points, lost-in-the-middle) (frontier)
- Query transformation (HyDE, decomposition, step-back, RAG-Fusion+RRF) (frontier)
- Hybrid search & re-ranking (BM25+dense, cross-encoders, ColBERT, MMR) (frontier)
- Advanced indexing (parent-doc, sentence-window, auto-merging, Anthropic Contextual Retrieval) (frontier)
- Agentic RAG (Self-RAG, CRAG, Adaptive-RAG, iterative, routing) (frontier)
- GraphRAG (Microsoft, Leiden communities, hybrid graph+vector) (frontier)
- RAG evaluation (Ragas, retrieval-vs-generation split) (frontier)
- Multimodal RAG (ColPali) + long-context-vs-RAG routing (frontier)
Frontier under this node: Advanced indexing (parent-doc, sentence-window, auto-merging, Anthropic Contextual Retrieval), Agentic RAG (Self-RAG, CRAG, Adaptive-RAG, iterative, routing), GraphRAG (Microsoft, Leiden communities, hybrid graph+vector), Hybrid search & re-ranking (BM25+dense, cross-encoders, ColBERT, MMR), Multimodal RAG (ColPali) + long-context-vs-RAG routing, Naive-RAG failure taxonomy (Barnett 7 points, lost-in-the-middle), Query transformation (HyDE, decomposition, step-back, RAG-Fusion+RRF), RAG evaluation (Ragas, retrieval-vs-generation split)