{"total":14,"rows":[{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"id":"2502.18993","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","created":"2025-02-26","cited_by_count":16,"area":"rag"},{"id":"2412.11854","title":"Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference","created":"2024-12-16","cited_by_count":15,"area":"rag"},{"id":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2503.01346","title":"SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph","created":"2025-03-03","cited_by_count":11,"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":"2504.08930","title":"VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG","created":"2025-04-11","cited_by_count":3,"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":"2606.02643","title":"Inference Cost Attacks for Retrieval-Augmented Large Language Models","created":"2026-05-31","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":"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":"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}