{"total":17,"rows":[{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452,"area":"rag"},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2404.08189","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","created":"2024-04-12","cited_by_count":93,"area":"rag"},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77,"area":"rag"},{"id":"2403.10059","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","created":"2024-03-15","cited_by_count":55,"area":"rag"},{"id":"2408.09199","title":"TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems","created":"2024-08-17","cited_by_count":28,"area":"rag"},{"id":"2401.14021","title":"Accelerating Retrieval-Augmented Language Model Serving with Speculation","created":"2024-01-25","cited_by_count":20,"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":"2503.03434","title":"RASD: Retrieval-Augmented Speculative Decoding","created":"2025-03-05","cited_by_count":6,"area":"rag"},{"id":"2505.12731","title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","created":"2025-05-19","cited_by_count":6,"area":"rag"},{"id":"2504.01281","title":"Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding","created":"2025-04-02","cited_by_count":5,"area":"rag"},{"id":"2510.15312","title":"Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution","created":"2025-10-17","cited_by_count":5,"area":"rag"},{"id":"2604.14885","title":"RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding","created":"2026-04-16","cited_by_count":4,"area":"rag"},{"id":"2504.11197","title":"Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance","created":"2025-04-15","cited_by_count":2,"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":"2511.20662","title":"Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability","created":"2025-11-03","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"}],"next_cursor":null}