Pith. sign in

REVIEW 13 cited by

Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.00054 v1 pith:Q32VU7BR submitted 2025-05-28 cs.IR cs.CL

Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

classification cs.IR cs.CL
keywords retrievalgenerationarchitecturesefficiencyretrieval-augmentedrobustnesssurveychallenges
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of parametric knowledge storage-such as factual inconsistency and domain inflexibility-it introduces new challenges in retrieval quality, grounding fidelity, pipeline efficiency, and robustness against noisy or adversarial inputs. This survey provides a comprehensive synthesis of recent advances in RAG systems, offering a taxonomy that categorizes architectures into retriever-centric, generator-centric, hybrid, and robustness-oriented designs. We systematically analyze enhancements across retrieval optimization, context filtering, decoding control, and efficiency improvements, supported by comparative performance analyses on short-form and multi-hop question answering tasks. Furthermore, we review state-of-the-art evaluation frameworks and benchmarks, highlighting trends in retrieval-aware evaluation, robustness testing, and federated retrieval settings. Our analysis reveals recurring trade-offs between retrieval precision and generation flexibility, efficiency and faithfulness, and modularity and coordination. We conclude by identifying open challenges and future research directions, including adaptive retrieval architectures, real-time retrieval integration, structured reasoning over multi-hop evidence, and privacy-preserving retrieval mechanisms. This survey aims to consolidate current knowledge in RAG research and serve as a foundation for the next generation of retrieval-augmented language modeling systems.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

    cs.CL 2025-12 unverdicted novelty 7.0

    M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.

  2. Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG

    cs.CL 2025-11 conditional novelty 7.0

    TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.

  3. Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.

  4. Reliable Evaluation Protocol for Low-Precision Retrieval

    cs.IR 2025-08 unverdicted novelty 6.0

    Proposes High-Precision Scoring (HPS) and Tie-aware Retrieval Metrics (TRM) to reduce tie-induced instability in low-precision retrieval evaluation.

  5. TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization

    cs.LG 2026-07 reject novelty 5.0

    A case study of TurboQuant for enterprise RAG reports a large recall advantage over product quantization, but the advantage depends on an unequal memory comparison.

  6. Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

    cs.CL 2026-07 conditional novelty 5.0

    Hybrid RAG over UK public health guidance sharply raises MCQA accuracy and free-form faithfulness, letting smaller open models match larger closed models without retrieval.

  7. Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics

    cs.IR 2026-06 unverdicted novelty 5.0

    Schema-First Retrieval embeds catalog metadata rather than rows and uses parallel retrieval plus reranking to raise table and column recall and cut SQL execution errors on three benchmarks.

  8. VikingMem: A Memory Base Management System for Stateful LLM-based Applications

    cs.AI 2026-05 unverdicted novelty 5.0

    VikingMem implements the Memory Base paradigm via event-centric extraction and entity updates on VikingDB with temporal compression, claiming up to 30% better retrieval effectiveness on long-term memory benchmarks.

  9. Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis

    cs.CR 2026-05 unverdicted novelty 5.0

    RAG frequently degrades LLM malware explanations when structured VirusTotal input is already available by introducing irrelevant context and narrative noise.

  10. Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents

    cs.IR 2026-04 conditional novelty 5.0

    Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.

  11. Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

    cs.CR 2026-04 unverdicted novelty 5.0

    SLOT organizes RAG security literature by attack Surface, defense Layer, CIA Objective, and Target scope, exposing mismatches between attacks and defenses along a six-stage knowledge pipeline.

  12. Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

    cs.CR 2026-04 accept novelty 5.0

    This paper establishes a taxonomy of RAG security organized around six workflow stages, three trust boundaries, and four primary security surfaces, while reviewing attacks, defenses, and gaps in current protections.

  13. Retrieval-Augmented LLMs for Security Incident Analysis

    cs.CR 2026-03 accept novelty 5.0

    A RAG system with query-based log filtering achieves up to 94% recall in malware incident analysis and 96% attack-step detection, with ablation studies confirming the filtering step is essential.