Retrieval-Augmented Generation for Large Language Models: A Survey

2023/12/18 by Yunfan Gao, Yun Xiong, Gao, Yunfan +15 · 386 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2312.10997

openalex publication_date 2023/12/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.

Cited by

• DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding
• Flexible Keyword-Aware Top-k Route Search
• RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
• Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
• DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation
• Selecting Language Models for Social Science: Start Small, Start Open, and Validate
• VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy
• ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control
• SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task
• Auditing Institutional Heterogeneity for Generative AI in Patient Education: A Large-Scale Study of 102 US Transplant Handbooks
• HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering
• Structure Over Scale: Schema-Constrained Causal Graphs for RAG
• Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
• Bridging Psychometric and Content Development Practices with AI: A Community-Based Workflow for Augmenting Hawaiian Language Assessments
• SPOT!: Map-Guided LLM Agent for Unsupervised Multi-CCTV Dynamic Object Tracking
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• CIRR: Causal-Invariant Retrieval-Augmented Recommendation with Faithful Explanations under Distribution Shift
• Graph-based Nearest Neighbors with Dynamic Updates via Random Walks
• The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models
• Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems
• Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
• SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems
• CogDoc: Towards Unified thinking in Documents
• Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy
• PathFinder: MCTS and LLM Feedback-based Path Selection for Multi-Hop Question Answering
• Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly
• LLMs in Interpreting Legal Documents
• Knowledge-Augmented Large Language Model Agents for Explainable Financial Decision-Making
• Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
• Information-Dense Reasoning for Efficient and Auditable Security Alert Triage
• Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
• Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understanding
• Learning to Code with Context: A Study-Based Approach
• The Road of Adaptive AI for Precision in Cybersecurity
• A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems
• AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
• The Personalization Paradox: Semantic Loss vs. Reasoning Gains in Agentic AI Q&A
• Memory-Guided Point Cloud Completion for Dental Reconstruction
• Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression
• LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM
• Breaking It Down: Domain-Aware Semantic Segmentation for Retrieval Augmented Generation
• Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
• An LLM-Assisted Multi-Agent Control Framework for Roll-to-Roll Manufacturing Systems
• RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms
• MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report)
• Geometrically-Constrained Agent for Spatial Reasoning
• EWE: An Agentic Framework for Extreme Weather Analysis
• Large Language Model Aided Birt-Hogg-Dube Syndrome Diagnosis with Multimodal Retrieval-Augmented Generation
• Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach
• Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation
• SmartPoC: Generating Executable and Validated PoCs for Smart Contract Bug Reports
• CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
• Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis
• Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
• Beyond Component Strength: Synergistic Integration and Adaptive Calibration in Multi-Agent RAG Systems
• Goal-Directed Search Outperforms Goal-Agnostic Memory Compression in Long-Context Memory Tasks
• Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems
• SemanticCite: Citation Verification with AI-Powered Full-Text Analysis and Evidence-Based Reasoning
• On 10x Better Scalability: KV Stores Scale Up KV Cache
• iLTM: Integrated Large Tabular Model
• Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
• Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of Biomechanics
• RAG-Driven Data Quality Governance for Enterprise ERP Systems
• NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
• LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
• RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
• Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor
• Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans
• BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
• JobSphere: An AI-Powered Multilingual Career Copilot for Government Employment Platforms
• CC30k: A Citation Contexts Dataset for Reproducibility-Oriented Sentiment Analysis
• Structured RAG for Answering Aggregative Questions
• Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety
• Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
• ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning
• Evaluation of retrieval-based QA on QUEST-LOFT
• CoEdge-RAG: Optimizing Hierarchical Scheduling for Retrieval-Augmented LLMs in Collaborative Edge Computing
• Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations
• Code Review Automation using Retrieval Augmented Generation
• Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
• SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents
• RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG
• LLM-enhanced Air Quality Monitoring Interface via Model Context Protocol
• Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications
• An LLM-powered MILP modelling engine for workforce scheduling guided by expert knowledge
• Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning
• Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
• Evaluating Cultural Knowledge Processing in Large Language Models: A Cognitive Benchmarking Framework Integrating Retrieval-Augmented Generation
• Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models
• OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights
• What's the next frontier for Data-centric AI? Data Savvy Agents
• AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
• GDPR-Bench-Android: A Benchmark for Evaluating Automated GDPR Compliance Detection in Android
• Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
• Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation
• InfoFlow: Reinforcing Search Agent Via Reward Density Optimization
• The novel vector database
• Model Inversion Attacks Meet Cryptographic Fuzzy Extractors
• Position: Biology is the Challenge Physics-Informed ML Needs to Evolve
• RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
• DMF: A Deterministic Memory Framework for Conversational AI Agents
• How well LLM-based test generation techniques perform with newer LLM versions?
• ScaleCall -- Agentic Tool Calling at Scale for Fintech: Challenges, Methods, and Deployment Insights
• Optimizing Retrieval for RAG via Reinforced Contrastive Learning
• Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansion
• The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems
• Structured Interfaces for Automated Reasoning with 3D Scene Graphs
• Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
• Reinforcement Learning for Long-Horizon Multi-Turn Search Agents
• Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation
• Hybrid Modeling, Sim-to-Real Reinforcement Learning, and Large Language Model Driven Control for Digital Twins
• Estimating the Error of Large Language Models at Pairwise Text Comparison
• Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
• Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective
• InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
• NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
• A Feasibility Study on Usability and Trust among Population Groups of a Medical Avatar Supported by Large Language Models with Retrieval Augmented Generation
• ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows
• From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
• FlexiDataGen: An Adaptive LLM Framework for Dynamic Semantic Dataset Generation in Sensitive Domains
• LightMem: Lightweight and Efficient Memory-Augmented Generation
• WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
• Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents
• Enhancing Hotel Recommendations with AI: LLM-Based Review Summarization and Query-Driven Insights
• AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
• Approximate Nearest Neighbor Search of Large Scale Vectors on Distributed Storage
• Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
• AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction
• Interpretability Framework for LLMs in Undergraduate Calculus
• Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarization
• An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs
• Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
• MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
• Automated Extraction of Protocol State Machines from 3GPP Specifications with Domain-Informed Prompts and LLM Ensembles
• MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems
• Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
• Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
• RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge
• LLM-REVal: Can We Trust LLM Reviewers Yet?
• ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
• What Generative Search Engines Like and How to Optimize Web Content Cooperatively
• Is Implicit Knowledge Enough for LLMs? A RAG Approach for Tree-based Structures
• Gobernanza y trazabilidad "a prueba de AI Act" para casos de uso legales: un marco técnico-jurídico, métricas forenses y evidencias auditables
• PRISM: Enhancing Protein Inverse Folding through Fine-Grained Retrieval on Structure-Sequence Multimodal Representations
• VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
• RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
• CacheClip: Accelerating RAG with Effective KV Cache Reuse
• Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning
• LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
• Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
• Gold Panning: Turning Positional Bias into Signal for Multi-Document LLM Reasoning
• DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
• Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learning
• DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
• EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
• Fundamentals of Building Autonomous LLM Agents
• RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
• VoiceAgentBench: Are Voice Assistants ready for agentic tasks?
• MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model
• An empirical study on declined proposals: why are these proposals declined?
• SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
• Autoformalizer with Tool Feedback
• A conversational tool for AI-driven feedback for UML modeling
• Large Language Models can extract morphological data from taxonomic descriptions, but their stochastic nature makes automation challenging: a test on Australian Asteraceae
• ConCuR: Conciseness Makes State-of-the-Art Kernel Generation
• Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems
• Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs
• CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
• DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Base
• RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
• MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
• Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
• Contrastive Retrieval Heads Improve Attention-Based Re-Ranking
• Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards
• AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning
• UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG
• Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
• External Data Extraction Attacks against Retrieval-Augmented Large Language Models
• SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?
• Panorama: Fast-Track Nearest Neighbors
• Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
• Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
• Retrieval-Augmented Generation for Electrocardiogram-Language Models
• Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval
• MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
• Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
• RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
• Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
• SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
• Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
• FreeRet: MLLMs as Training-Free Retrievers
• HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing
• Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow
• Transparency of medical artificial intelligence systems
• Retrieval-Constrained Decoding Reveals Underestimated Parametric Knowledge in Language Models
• Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs
• Aitomia: An Agentic Framework for AI-Driven Atomistic and Quantum Chemical Simulations
• LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
• Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
• Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
• In-Context Learning can Perform Continual Learning Like Humans
• GeoEvolve: Automating Geospatial Model Discovery via Multi-Agent Large Language Models
• Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
• Query-Centric Graph Retrieval Augmented Generation
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning
• Beyond Stars: Bridging the Gap Between Ratings and Review Sentiment with LLM
• RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
• Can LLMs Forecast Internet Traffic from Social Media?
• Enhancing LLM-based Fault Localization with a Functionality-Aware Retrieval-Augmented Generation Framework
• Hallucination‐Free? Assessing the Reliability of Leading AI Legal Research Tools
• AgentClinic: a multimodal benchmark for tool-using clinical AI agents
• LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation
• The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality
• GRAPHxx: DSML engineering for knowledge graph building and streamlining with GraphRAG
• ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models
• AI-enhanced reference services in special libraries: a case study of the Hakka Literary Museum
• Modeling Diabetes Risk and Progression With Public Health Data: Ontology-Guided, Simulation-Capable Digital Twin Study
• Advances in Large Language Models for Medicine
• Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
• Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications
• Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
• A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
• RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code
• Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever
• UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
• Evaluating Retrieval-Augmented Generation Strategies for Large Language Models in Travel Mode Choice Prediction
• Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
• Orion: Fuzzing Workflow Automation
• Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
• Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
• Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
• SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework
• A Scenario-Driven Cognitive Approach to Next-Generation AI Memory
• Harnessing the Power of AI in Qualitative Research: Role Assignment, Engagement, and User Perceptions of AI-Generated Follow-Up Questions in Semi-Structured Interviews
• H²R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents
• SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
• Exposing Privacy Risks in Graph Retrieval-Augmented Generation
• Large Language Models Imitate Logical Reasoning, but at what Cost?
• EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
• LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering
• Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration
• Filtered Approximate Nearest Neighbor Search: A Unified Benchmark and Systematic Experimental Study [Experiment, Analysis & Benchmark]
• FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support
• Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
• Towards End-to-End Model-Agnostic Explanations for RAG Systems
• Intelligent Manufacturing Support: Specialized LLMs for Composite Material Processing and Equipment Operation
• Beamforming-LLM: What, Where and When Did I Miss?
• HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
• Language Native Lightly Structured Databases for Large Language Model Driven Composite Materials Research
• Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial
• Stack Overflow Is Not Dead Yet: Crowd Answers Still Matter
• EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
• MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation
• SasAgent: Multi-Agent AI System for Small-Angle Scattering Data Analysis
• Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
• Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
• CMRAG: Co-modality-based visual document retrieval and question answering
• Generative KI für TA
• Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts
• LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents
• VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples
• Tether: A Personalized Support Assistant for Software Engineers with ADHD
• Application Of Large Language Models For The Extraction Of Information From Particle Accelerator Technical Documentation
• Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
• MeVe: A Modular System for Memory Verification and Effective Context Control in Language Models
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
• Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation
• QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting
• Identifying Origins of Place Names via Retrieval Augmented Generation
• RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring
• Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?
• Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification
• OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews
• Data Auctions for Retrieval Augmented Generation
• Data-driven Discovery of Digital Twins in Biomedical Research
• LLM-driven Provenance Forensics for Threat Investigation and Detection
• Addressing accuracy and hallucination of LLMs in Alzheimer's disease research through knowledge graphs
• An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs
• AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
• End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
• GoVector: An I/O-Efficient Caching Strategy for High-Dimensional Vector Nearest Neighbor Search
• SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation
• From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data
• Socially Interactive Agents for Preserving and Transferring Tacit Knowledge in Organizations
• Orchid: Orchestrating Context Across Creative Workflows with Generative AI
• MQAD: A Large-Scale Question Answering Dataset for Training Music Large Language Models
• Mitigating Clinician Information Overload: Generative AI for Integrated EHR and RPM Data Analysis
• Conflict-Aware Soft Prompting for Retrieval-Augmented Generation
• Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Index
• Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework
• Strata: Hierarchical Context Caching for Long Context Language Model Serving
• Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
• Beyond Benchmark: LLMs Evaluation with an Anthropomorphic and Value-oriented Roadmap
• Views: a hardware-friendly graph database model for storing semantic information
• Identifying and Answering Questions with False Assumptions: An Interpretable Approach
• Cohort-Aware Agents for Individualized Lung Cancer Risk Prediction Using a Retrieval-Augmented Model Selection Framework
• LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents
• Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration
• AdaptJobRec: Enhancing Conversational Career Recommendation through an LLM-Powered Agentic System
• Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward
• GeoGPT-RAG Technical Report
• Contrastive Representations for Temporal Reasoning
• AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation
• Chain of Prompts and Memories for Accessible Symbolic Applications in the Legal Domain
• Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverables
• A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation
• Can we Evaluate RAGs with Synthetic Data?
• AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
• Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
• Retrieval-augmented reasoning with lean language models
• Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering
• AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
• Bias is a Math Problem, AI Bias is a Technical Problem: 10-year Literature Review of AI/LLM Bias Research Reveals Narrow [Gender-Centric] Conceptions of 'Bias', and Academia-Industry Gap
• SoK: Data Minimization in Machine Learning
• Bridging Solidity Evolution Gaps: An LLM-Enhanced Approach for Smart Contract Compilation Error Resolution
• A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction
• Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
• SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling
• Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
• DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation
• Exploring the Challenges and Opportunities of AI-assisted Codebase Generation
• Towards Multimodal Sentiment Analysis via Contrastive Cross-modal Retrieval Augmentation and Hierachical Prompts
• Retrieval-Augmented Multi-Agent System for Rapid Statement of Work Generation
• Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation
• Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond
• LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference
• HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways
• Automated Formalization via Conceptual Retrieval-Augmented LLMs
• Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs
• Information retrieval or document retrieval? Terminological confusions and unrealistic goals in information science, exemplified in relation to generative artificial intelligence
• Exploring a biocentric LLM-based assistant in environmental decision-making with more-than-human representation of the Tagus Estuary
• Classification is a RAG problem: A case study on hate speech detection
• UR²: Unify RAG and Reasoning through Reinforcement Learning
• First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models
• Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime
• You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
• RTTC: Reward-Guided Collaborative Test-Time Compute
• GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning
• Empowering Time Series Forecasting with LLM-Agents
• WARP -- Web-Augmented Real-time Program Repairer: A Real-Time Compilation Error Resolution using LLMs and Web-Augmented Synthesis
• PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
• MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation
• PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
• A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering
• ASINT: Learning AS-to-Organization Mapping from Internet Metadata
• Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning
• RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
• Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations
• ReMoMask: Retrieval-Augmented Masked Motion Generation
• Dialogue Systems Engineering: A Survey and Future Directions
• CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
• A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
• RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems
• MaRGen: Multi-Agent LLM Approach for Self-Directed Market Research and Analysis
• LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
• Lucy: edgerunning agentic web search on mobile with machine generated task vectors
• Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation
• AutoBridge: Automating Smart Device Integration with Centralized Platform
• Comparison of Large Language Models for Deployment Requirements
• How Far Are AI Scientists from Changing the World?
• ChatVis: Large Language Model Agent for Generating Scientific Visualizations
• From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
• Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
• Towards a rigorous evaluation of RAG systems: the challenge of due diligence
• Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering
• MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration
• Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented Generation
• OmniBench-RAG: A Multi-Domain Evaluation Platform for Retrieval-Augmented Generation Tools
• A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
• SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation
• Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models
• Enhancing RAG Efficiency with Adaptive Context Compression
• YATE: The Role of Test Repair in LLM-Based Unit Test Generation
• Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
• System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition
• A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
• SMARTAPS: Tool-augmented LLMs for Operations Management
• QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
• uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs
• Business Utility of Large Language Models as Exploratory Data Analysis Agents
• Generative AI as a tool to accelerate the field of ecology
• TAI Scan Tool: A RAG-Based Tool With Minimalistic Input for Trustworthy AI Self-Assessment
• Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environments
• ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry

Related

• Retrieval-Augmented Generation for Natural Language Processing: A Survey
• A Survey on Retrieval-Augmented Text Generation for Large Language Models
• When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
• Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
• RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation