{"total":19,"rows":[{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2606.02553","title":"LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation","created":"2026-06-01","cited_by_count":16,"area":"rag"},{"id":"2406.09827","title":"A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention","created":"2024-06-14","cited_by_count":12,"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":"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":"2512.17220","title":"Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding","created":"2025-12-19","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":"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":"2509.17486","title":"AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation","created":"2025-09-22","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":"2511.14182","title":"WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web","created":"2025-11-18","cited_by_count":2,"area":"rag"},{"id":"2605.11864","title":"Very Efficient Listwise Multimodal Reranking for Long Documents","created":"2026-05-12","cited_by_count":2,"area":"rag"},{"id":"2606.28361","title":"ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services","created":"2026-06-13","cited_by_count":0,"area":"rag"},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","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":"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":"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}