{"total":53,"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":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105,"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":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"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":"2408.04259","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","created":"2024-08-08","cited_by_count":24,"area":"rag"},{"id":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","cited_by_count":20,"area":"rag"},{"id":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"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":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2406.11357","title":"Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities","created":"2024-06-17","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":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"area":"rag"},{"id":"2406.19251","title":"AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation","created":"2024-06-27","cited_by_count":13,"area":"rag"},{"id":"2409.15895","title":"Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation","created":"2024-09-24","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":"2410.07589","title":"No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users","created":"2024-10-10","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":"2403.15268","title":"Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering","created":"2024-03-22","cited_by_count":7,"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":"2502.13465","title":"HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks","created":"2025-02-19","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":"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":"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":"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":"2506.12494","title":"FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation","created":"2025-06-14","cited_by_count":2,"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":"2603.09222","title":"EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering","created":"2026-03-10","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":"2605.30790","title":"On the impact of retrieved content representations in RAG Pipelines","created":"2026-05-29","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":"2607.00725","title":"Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented Generation","created":"2026-07-01","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":"2506.02503","title":"KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG","created":"2025-06-03","cited_by_count":0,"area":"rag"},{"id":"2604.14403","title":"A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation","created":"2026-04-15","cited_by_count":0,"area":"rag"},{"id":"2605.26165","title":"Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets","created":"2026-05-24","cited_by_count":0,"area":"rag"},{"id":"2607.16209","title":"Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning","created":"2026-05-10","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":"2608.03148","title":"Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation","created":"2026-08-04","cited_by_count":0,"area":"rag"},{"id":"2608.19535","title":"From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG","created":"2026-08-20","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":"2609.05760","title":"RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems","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":"2609.14245","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":"2609.27380","title":"MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression","created":"2026-09-23","cited_by_count":0,"area":"rag"}],"next_cursor":null}