cs.AIOct 1, 2026
SaveMapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
Organizations: School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India. · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.
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.
Figures & tables
Fig. 1 : Overview of the four taxonomic dimensions of RAG systems explored in this survey: Compression and Efficiency , Defensive RAG , User-Centric Interaction , and Complex Reasoning . These axes represent key directions in optimizing performance, improving security and fairness, aligning with user intent, and supporting structured reasoning.
Fig. 2 : Overview of the Retrieval-Augmented Generation (RAG) pipeline. The workflow is divided into two phases: (1) offline indexing, where source documents are chunked, encoded into dense embeddings, and stored in a vector database; and (2) online retrieval and generation, where the user query is embedded and used to retrieve the top-k semantically relevant document chunks via vector similarity search. The retrieved context is combined with the original query and supplied to the large language model (LLM), enabling grounded and context-aware response generation.
| Survey | Year | Focus Area | What They Cover | What They Don’t Cover | What This Survey Adds |
|---|---|---|---|---|---|
| Brehme et al. [ 55 ] | 2025 | RAG evaluation | LLM judges, dataset scoring | Indexing and component-wise evaluation | Four-axis taxonomy (efficiency, defense, interactivity, reasoning) beyond evaluation methodology alone |
| Hindi et al. [ 56 ] | 2025 | Legal-domain RAG | Interpretability, legal datasets | Generalizable evaluation methods | Domain-independent four-axis taxonomy, not limited to a single domain |
| Ni et al. [ 57 ] | 2025 | Trustworthy RAG | Safety, robustness, fairness | Dataset/index/generation evaluation | Extends safety/robustness focus with three further axes: efficiency, interactivity, and reasoning |
| Zheng et al. [ 58 ] | 2025 | Vision-based RAG | Multimodal retrieval and generation | Text-only methodological evaluation | Four-axis taxonomy for text-based RAG, complementing multimodal-focused coverage |
| Oche et al. [ 59 ] | 2025 | Systematic RAG review | Year-wise progress, industry trends | Limited methodological depth | Formalizes each axis via objective, algorithm, and literature synthesis, beyond trend-level review |
| Singh et al. [ 26 ] | 2025 | Agentic RAG | Planning, tool-use, autonomous agents | Evaluation of core RAG components | Clarifies boundary between agentic RAG and this survey’s four-axis architectural taxonomy |
TABLE I : Comparison of prior RAG surveys and the contributions of this work.
| Method | Retrieval | Comp./cost | Multi-step | Safety | Personal. | Structured | Verify | Primary RQ |
| Compression & Efficiency (RQ1) | ||||||||
| RAPTOR [ 46 ] | Dense | ✓ | ✓ | RQ1 | ||||
| xRAG [ 60 ] | Dense | ✓ | RQ1 | |||||
| RQ-RAG [ 61 ] | Dense | ✓ | ✓ | RQ1 | ||||
| Stochastic RAG [ 62 ] | Dense | ✓ | RQ1 | |||||
| Defensive RAG (RQ2) | ||||||||
TABLE II : Cross-axis comparison of representative RAG methods. Each method is marked (✓) with the cross-cutting design features it exhibits and the research question(s) it primarily addresses. Feature columns: Comp./cost -compression- or cost-aware context selection; Multi-step -retrieval interleaved across reasoning or refinement steps; Safety -toxicity, bias, or privacy filtering; Personal. -user/history-conditioned retrieval; Structured -retrieval over graphs, tables, or other structure; Verify -critique or verification of retrieved evidence.
Fig. 3 : Schematic of Compression and Efficiency-Driven RAG systems.
Fig. 4 : Comparison between standard and defensive RAG pipelines, illustrating safeguards for harmful content detection, prompt sanitization, and bias-aware document retrieval.
Fig. 5 : Comparison between Normal RAG and Interactive, User-Centric RAG architectures.
Fig. 6 : Illustration of Normal RAG versus Complex Reasoning RAG. While the Naive RAG pipeline retrieves documents and generates a direct response to the initial query, the Complex Reasoning RAG decomposes the query into sub-questions, performs stepwise retrieval, and incrementally builds a structured, multi-step response tailored to complex information needs.
| Method | Dataset / Setting | Accuracy / F1 | Hallucination / Consistency | Retrieval Effectiveness |
|---|---|---|---|---|
| FoRAG | WebGPT (en), WebCPM (zh) | Factuality: 0.82–0.99 | Coherence: 0.91–0.98 | Training Time (Holistic): 33.1h |
| WeKnow-RAG | 4 domains, classification, chunk-size eval | Accuracy: 0.10–0.41 | Hallucination: 0.025–0.35 | Confidence-aware retrieval analysis |
| GenGround | HotpotQA, MuSiQue, StrategyQA | F1: 27.3–52.3 | Semantic Acc: 24.7–55.7 | - |
| FRAMES | Internal multi-hop QA benchmark | Acc: 0.408–0.729 | - | Prompting strategy comparison |
| Adobe RAG | Adobe product corpus | nDCG: 0.692–0.822 | - | Dataset coverage breakdown |
| Self-RAG (TA-ARE) | RetrievalQA (various LLMs) | Match Acc: 6.0–46.4 | - | Retrieval Acc: up to 100% |
TABLE III : Performance metrics of QA-centric Retrieval-Augmented Generation models across multiple evaluation criteria. “-” indicates data not reported.
| Model | Datasets / Evaluation Context | Key Metrics / Findings |
|---|---|---|
| PoisonedRAG | NQ, HotpotQA, MS-MARCO | ASR: 0.97–0.99; F1-Score: 0.96–1.00 |
| RAG (CoCondenser + MiniLM) | Government, Education, Society, Health | ASR: 0.17–0.50; ASV: –0.17 to 0.67 |
| RC-RAG | Internal eval on ChatGPT and Mistral | Risk: 14.94–19.00; Carefulness: 52.87–65.37 |
| Towards Fair RAG | Exposure Disparity Benchmarks | EE-D: 0.14; EE-R: 0.28 |
| LLaMA2-7B-Chat | Health, Enron Attacks | ROUGE Prompts: 73–111; Repeat Contexts: 55–135 |
| BadRAG | GPT-4, Claude-3 Evaluation | Retrieval Success: 98.9%; Rejection Rate: 74.6% |
TABLE IV : Overview of Security, Fairness, and Privacy-focused RAG Systems
| Model | Category | Attribute / Metric | Score / Description |
| GitHub Copilot | IDE Support | Supported IDEs | IntelliJ, VSCode, PyCharm, etc. |
| Reference / Explanation | Provides References | No | |
| Reference / Explanation | Explains Suggestions | No | |
| Suggestion Variety | Options Returned | Up to 10 | |
| Training Source | Data | Public Repositories | |
| Languages Supported | Best With | C, C++, Java, Python, etc. |
TABLE V: Comparison of Retrieval-Based Code Generation Systems and Metrics
| Model | Metric | Details |
|---|---|---|
| LLaMA2 | Precision | 89% |
| Recall | 84.5% | |
| Accuracy | 85% | |
| [1pt/1pt] RAG (Cost across prompting strategies) | Zero-shot Prompt Type I (GPT-3.5 Turbo) | $0.100 |
| Zero-shot Prompt Type II (GPT-3.5 Turbo) | $0.014 | |
| Tree of Thoughts Prompt (GPT-3.5 Turbo) | $0.013 |
TABLE VI : Evaluation of RAG-based and LLM-enhanced systems in educational and corporate contexts
| Model | Metric | Values and Evaluation Details |
| RAST (Style Transfer) | BLEU Scores (SQuAD/1) | Top-1: 19.25, Oracle: 23.23, Pairwise: 48.91, Overall: 9.14 |
| BLEU Scores (SQuAD/2) | Top-1: 19.36, Oracle: 22.59, Pairwise: 56.42, Overall: 7.75 | |
| BLEU Scores (NewsQA) | Top-1: 11.02, Oracle: 16.26, Pairwise: 23.16, Overall: 7.74 | |
| [1pt/1pt] bge-large-en-v1.5 | NDCG@10 | 0.85 |
| Accuracy@k (Combined vs. Separate DBs) | k=1: 0.85 / 0.91, k=5: 0.92 / 0.95, k=10: 0.93 / 0.97 | |
| Training/Test Split | Written: 1450 / 500, Transcribed: 1450 / 500 |
TABLE VII : Metrics and Evaluation Results for RAG-based Corporate Knowledge Management Systems
| Model | Setting / Task | Precision / Recall / F1 | Other Metrics / Notes |
|---|---|---|---|
| CaseGPT | Medical, Legal Domain QA | Medical: Precision@10: 0.90, F1: 0.89 Legal: Precision@10: 0.93, F1: 0.91 | MRR: 0.92 (med), 0.94 (legal) NDCG@10: 0.91/0.93 Human Scores: Quality: 4.3, Relevance: 4.5 |
| CBR-RAG | Case Law Legal QA | – | Top Statutes: Fed. Court Rules (9), Civil Aviation (8), etc. Improves grounding using legal precedent |
| LegalBench-RAG | Benchmark Evaluation | – | Q&A Counts: CUAD (4042), MAUD (1676), etc. Total Q&A: 6858 |
| HyPA-RAG | Hybrid Retrieval + Adaptation | Context Recall: 0.9046 Faithfulness: 0.8430 F1 Similarity: 0.8621 | Correctness (1-5): 4.25 PA-Class (2/3): 0.90/0.89 Answer Relevancy: 0.79 / 0.77 |
TABLE VIII : Evaluation of RAG Models for Scientific and Legal Text Processing