{"total":43,"rows":[{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37,"area":"rag"},{"id":"2412.10543","title":"METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation","created":"2024-12-13","cited_by_count":17,"area":"rag"},{"id":"2602.02579","title":"ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation","created":"2026-01-31","cited_by_count":13,"area":"rag"},{"id":"2512.16822","title":"MEPIC: Memory Efficient Position Independent Caching for LLM Serving","created":"2025-12-18","cited_by_count":11,"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":"2511.17560","title":"$A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving","created":"2025-11-13","cited_by_count":8,"area":"rag"},{"id":"2607.01299","title":"HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching","created":"2026-07-01","cited_by_count":7,"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":"2601.12904","title":"From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":5,"area":"rag"},{"id":"2603.20218","title":"An experimental study of KV cache reuse strategies in chunk-level caching systems","created":"2026-03-03","cited_by_count":5,"area":"rag"},{"id":"2603.23049","title":"PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving","created":"2026-03-24","cited_by_count":4,"area":"rag"},{"id":"2607.17715","title":"C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference","created":"2026-07-20","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":"2603.05353","title":"InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context","created":"2026-03-05","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":"2410.20299","title":"EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update","created":"2024-10-27","cited_by_count":2,"area":"rag"},{"id":"2504.15302","title":"RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU","created":"2025-04-17","cited_by_count":2,"area":"rag"},{"id":"2606.04302","title":"LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding","created":"2026-06-03","cited_by_count":2,"area":"rag"},{"id":"2606.13126","title":"MiniPIC: Flexible Position-Independent Caching in <100LOC","created":"2026-06-11","cited_by_count":2,"area":"rag"},{"id":"2606.21842","title":"Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAG","created":"2026-06-20","cited_by_count":2,"area":"rag"},{"id":"2607.04281","title":"Risk-Constrained Freshness-Aware Semantic Caching for Open-Web Retrieval-Augmented LLMs","created":"2026-07-05","cited_by_count":2,"area":"rag"},{"id":"2505.10951","title":"SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache","created":"2025-05-16","cited_by_count":1,"area":"rag"},{"id":"2601.08670","title":"Parallel Context-of-Experts Decoding for Retrieval Augmented Generation","created":"2026-01-13","cited_by_count":1,"area":"rag"},{"id":"2601.11553","title":"PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices","created":"2025-12-10","cited_by_count":1,"area":"rag"},{"id":"2604.25080","title":"CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2605.08581","title":"PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design","created":"2026-05-09","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":"2606.19667","title":"CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference","created":"2026-06-18","cited_by_count":1,"area":"rag"},{"id":"2607.01831","title":"Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference","created":"2026-07-02","cited_by_count":1,"area":"rag"},{"id":"2609.17983","title":"Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits","created":"2026-09-16","cited_by_count":1,"area":"rag"},{"id":"2510.20878","title":"HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2605.15913","title":"Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation","created":"2026-05-15","cited_by_count":0,"area":"rag"},{"id":"2607.21599","title":"Decoupled Attention Fusion: Accelerating RAG with Efficient KV Cache Reuse","created":"2026-05-03","cited_by_count":0,"area":"rag"},{"id":"2607.26076","title":"FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents","created":"2026-07-14","cited_by_count":0,"area":"rag"},{"id":"2608.07458","title":"CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG","created":"2026-08-07","cited_by_count":0,"area":"rag"},{"id":"2608.30996","title":"Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation","created":"2026-08-31","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":"2609.09768","title":"Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?","created":"2026-09-09","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":"2609.33503","title":"RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse","created":"2026-09-27","cited_by_count":0,"area":"rag"},{"id":"2609.35139","title":"CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion","created":"2026-09-28","cited_by_count":0,"area":"rag"},{"id":"2610.15186","title":"SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG","created":"2026-10-10","cited_by_count":0,"area":"rag"}],"next_cursor":null}