Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning

The paper surveys recent advances in Retrieval Augmented Generation (RAG), a technique that integrates external retrieval into language model generation to reduce hallucinations and keep knowledge current. It introduces a four‑axis taxonomy—efficiency, defense, interactivity, and reasoning—to organize contemporary RAG research, covering retrieval methods, fusion strategies, embedding optimizations, and reinforcement learning policies. The survey also reviews evaluation practices, domain‑specific applications, and architectural variants, while highlighting ongoing challenges such as retrieval quality, reliability, domain adaptation, scalability, and explainability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• rag
• reinforcement-learning
• fine-tuning