Survey maps retrieval augmented generation advances and challenges
Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
Artificial Intelligence
Summary
Large language models can generate text but sometimes make up facts or only know what they learned before. The authors review ways to improve these models by letting them search external information while writing. They organize progress into four areas: making searches faster, making outputs more trustworthy, supporting interactive use, and helping with complex reasoning. They also discuss different methods, how people evaluate these systems, and ongoing challenges like making search results more accurate and adaptable.
What this means in practice
- •For software architects: Design complex language systems that combine retrieval and generation with improved efficiency and reliability based on a structured taxonomy of RAG methods.
- •For enterprise ai teams: Build interactive document assistants that safely incorporate up-to-date external knowledge by following best practices summarized for retrieval augmented generation.
A survey. It maps existing work.
Authors
Meghana Sunil, Shravya V, Shravan Venkatraman, Joe Dhanith PR
Abstract
Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and their susceptibility to hallucinating information. Retrieval Augmented Generation (RAG) addresses these issues by incorporating external retrieval into the generation process, grounding model outputs in verifiable and up to date sources. While prior surveys primarily focus on core RAG architectures and standard pipelines, recent research explores broader challenges and capabilities that extend beyond these foundational designs. This survey provides a consolidated and structured examination of contemporary RAG developments, organizing the field into a four axis taxonomy: improving retrieval efficiency, strengthening robustness and security, supporting user driven and interactive workflows, and enabling multi step or complex reasoning. We formalize key components of the RAG framework and review methods spanning dense and sparse retrieval, fusion strategies, embedding optimizations, and reinforcement learning based retrieval policies, highlighting how these advances influence practical deployment and system design. We also synthesize evaluation practices, domain specific applications, and architectural variants such as Naive, Advanced, and Modular RAG. Finally, we outline persistent challenges related to retrieval quality, reliability, domain adaptation, scalability, and explainability, and identify opportunities for building RAG systems that are more reliable, adaptable, and transparent.