{"total":20,"rows":[{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"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":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"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":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"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":"2505.16014","title":"Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains","created":"2025-05-21","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":"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":"2512.22195","title":"MatKV: Trading Compute for Flash Storage in LLM Inference","created":"2025-12-20","cited_by_count":2,"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":"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":"2608.25115","title":"Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting","created":"2026-08-25","cited_by_count":1,"area":"rag"},{"id":"2510.19644","title":"CoRoVA: Compressed Representations for Vector-Augmented Code Completion","created":"2025-10-22","cited_by_count":0,"area":"rag"},{"id":"2606.15179","title":"CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation","created":"2026-06-13","cited_by_count":0,"area":"rag"},{"id":"2608.15171","title":"P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving","created":"2026-08-15","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":"2610.09757","title":"EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented Generation","created":"2026-10-07","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}