{"total":88,"rows":[{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2409.05591","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","created":"2024-09-09","cited_by_count":119,"area":"rag"},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105,"area":"rag"},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2505.14069","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","created":"2025-05-20","cited_by_count":70,"area":"rag"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64,"area":"rag"},{"id":"2410.18050","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","created":"2024-10-23","cited_by_count":49,"area":"rag"},{"id":"2407.21059","title":"Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks","created":"2024-07-26","cited_by_count":42,"area":"rag"},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40,"area":"rag"},{"id":"2411.02959","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","created":"2024-11-05","cited_by_count":37,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2402.12174","title":"BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence","created":"2024-02-19","cited_by_count":28,"area":"rag"},{"id":"2407.15353","title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","created":"2024-07-22","cited_by_count":28,"area":"rag"},{"id":"2503.01478","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","created":"2025-03-03","cited_by_count":24,"area":"rag"},{"id":"2602.02007","title":"Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation","created":"2026-02-02","cited_by_count":19,"area":"rag"},{"id":"2501.11551","title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","created":"2025-01-20","cited_by_count":18,"area":"rag"},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2406.01549","title":"An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation","created":"2024-06-03","cited_by_count":16,"area":"rag"},{"id":"2406.11357","title":"Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities","created":"2024-06-17","cited_by_count":16,"area":"rag"},{"id":"2503.18174","title":"GINGER: Grounded Information Nugget-Based Generation of Responses","created":"2025-03-23","cited_by_count":16,"area":"rag"},{"id":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"id":"2505.15561","title":"Do RAG Systems Really Suffer From Positional Bias?","created":"2025-05-21","cited_by_count":12,"area":"rag"},{"id":"2504.04062","title":"QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors","created":"2025-04-05","cited_by_count":11,"area":"rag"},{"id":"2409.01579","title":"AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models","created":"2024-09-03","cited_by_count":10,"area":"rag"},{"id":"2502.13847","title":"DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue","created":"2025-02-19","cited_by_count":10,"area":"rag"},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2410.11315","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":9,"area":"rag"},{"id":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2410.23090","title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","created":"2024-10-30","cited_by_count":8,"area":"rag"},{"id":"2509.00877","title":"EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes","created":"2025-08-31","cited_by_count":8,"area":"rag"},{"id":"2605.10114","title":"SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution","created":"2026-05-11","cited_by_count":8,"area":"rag"},{"id":"2501.02844","title":"GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification","created":"2025-01-06","cited_by_count":7,"area":"rag"},{"id":"2409.15699","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","created":"2024-09-24","cited_by_count":6,"area":"rag"},{"id":"2409.13385","title":"Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2024-09-20","cited_by_count":5,"area":"rag"},{"id":"2505.11271","title":"Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models","created":"2025-05-16","cited_by_count":5,"area":"rag"},{"id":"2604.10734","title":"Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS","created":"2026-04-12","cited_by_count":5,"area":"rag"},{"id":"2406.08116","title":"Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling","created":"2024-06-12","cited_by_count":4,"area":"rag"},{"id":"2409.12468","title":"Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":4,"area":"rag"},{"id":"2505.11932","title":"Neuro-Symbolic Query Compiler","created":"2025-05-17","cited_by_count":4,"area":"rag"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2505.23277","title":"Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression","created":"2025-05-29","cited_by_count":4,"area":"rag"},{"id":"2506.05167","title":"ECoRAG: Evidentiality-guided Compression for Long Context RAG","created":"2025-06-05","cited_by_count":4,"area":"rag"},{"id":"2605.09611","title":"Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks","created":"2026-05-10","cited_by_count":4,"area":"rag"},{"id":"2507.09138","title":"HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving","created":"2025-07-12","cited_by_count":3,"area":"rag"},{"id":"2509.17486","title":"AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation","created":"2025-09-22","cited_by_count":3,"area":"rag"},{"id":"2606.05875","title":"QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving","created":"2026-06-04","cited_by_count":3,"area":"rag"},{"id":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2410.09662","title":"Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks","created":"2024-10-12","cited_by_count":2,"area":"rag"},{"id":"2410.10315","title":"EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations","created":"2024-10-14","cited_by_count":2,"area":"rag"},{"id":"2502.14925","title":"CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs","created":"2025-02-19","cited_by_count":2,"area":"rag"},{"id":"2503.02603","title":"OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing","created":"2025-03-04","cited_by_count":2,"area":"rag"},{"id":"2505.06569","title":"MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG","created":"2025-05-10","cited_by_count":2,"area":"rag"},{"id":"2505.12662","title":"Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering","created":"2025-05-19","cited_by_count":2,"area":"rag"},{"id":"2506.12494","title":"FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation","created":"2025-06-14","cited_by_count":2,"area":"rag"},{"id":"2508.13828","title":"Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration","created":"2025-08-19","cited_by_count":2,"area":"rag"},{"id":"2511.18832","title":"Concept than Document: Context Compression via AMR-based Conceptual Entropy","created":"2025-11-24","cited_by_count":2,"area":"rag"},{"id":"2601.01896","title":"Tackling the Inherent Difficulty of Noise Filtering in RAG","created":"2026-01-05","cited_by_count":2,"area":"rag"},{"id":"2405.02659","title":"R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models","created":"2024-05-04","cited_by_count":1,"area":"rag"},{"id":"2502.13019","title":"Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation","created":"2025-02-18","cited_by_count":1,"area":"rag"},{"id":"2504.03165","title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","created":"2025-04-04","cited_by_count":1,"area":"rag"},{"id":"2504.12673","title":"ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models","created":"2025-04-17","cited_by_count":1,"area":"rag"},{"id":"2506.22210","title":"UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses","created":"2025-06-27","cited_by_count":1,"area":"rag"},{"id":"2510.15620","title":"On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding","created":"2025-10-17","cited_by_count":1,"area":"rag"},{"id":"2601.08699","title":"RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis","created":"2026-01-13","cited_by_count":1,"area":"rag"},{"id":"2604.23734","title":"Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval","created":"2026-04-26","cited_by_count":1,"area":"rag"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2605.14503","title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","created":"2026-05-14","cited_by_count":1,"area":"rag"},{"id":"2605.27494","title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2606.13550","title":"Uncertainty-Aware Hybrid Retrieval for Long-Document RAG","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2606.21807","title":"Fixed RAG Compression Collapses Measured Reader Scaling","created":"2026-06-20","cited_by_count":1,"area":"rag"},{"id":"2608.13588","title":"IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering","created":"2026-07-12","cited_by_count":1,"area":"rag"},{"id":"2410.04790","title":"PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA","created":"2024-10-07","cited_by_count":0,"area":"rag"},{"id":"2512.08943","title":"Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models","created":"2025-11-19","cited_by_count":0,"area":"rag"},{"id":"2604.17325","title":"Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation","created":"2026-04-19","cited_by_count":0,"area":"rag"},{"id":"2608.00765","title":"RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation","created":"2026-08-01","cited_by_count":0,"area":"rag"},{"id":"2608.23252","title":"The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.11209","title":"REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.11390","title":"VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.14245","title":"The Attribution-Compression Frontier in Retrieval-Augmented Generation","created":"2026-09-13","cited_by_count":0,"area":"rag"},{"id":"2609.17564","title":"Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs","created":"2026-07-23","cited_by_count":0,"area":"rag"},{"id":"2609.22100","title":"AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation","created":"2026-08-12","cited_by_count":0,"area":"rag"},{"id":"2609.27380","title":"MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression","created":"2026-09-23","cited_by_count":0,"area":"rag"},{"id":"2609.37349","title":"TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG","created":"2026-09-29","cited_by_count":0,"area":"rag"}],"next_cursor":null}