{"total":17,"rows":[{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2503.04338","title":"In-depth Analysis of Graph-based RAG in a Unified Framework","created":"2025-03-06","cited_by_count":46,"area":"rag"},{"id":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","cited_by_count":28,"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":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2508.01405","title":"Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search","created":"2025-08-02","cited_by_count":4,"area":"rag"},{"id":"2512.08289","title":"MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks","created":"2025-12-09","cited_by_count":4,"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":"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":"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":"2505.16096","title":"Cosmos: A CXL-Based Full In-Memory System for Approximate Nearest Neighbor Search","created":"2025-05-22","cited_by_count":2,"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":"2608.03487","title":"RAG-Stack: Co-Optimizing RAG Serving Performance and Quality","created":"2026-08-04","cited_by_count":1,"area":"rag"},{"id":"2410.23805","title":"UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture","created":"2024-10-31","cited_by_count":0,"area":"rag"},{"id":"2505.07833","title":"Harmonia: End-to-End RAG Serving Optimization","created":"2025-05-01","cited_by_count":0,"area":"rag"},{"id":"2511.00855","title":"All-in-one Graph-based Indexing for Hybrid Search on GPUs","created":"2025-11-02","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"}],"next_cursor":null}