{"total":44,"rows":[{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"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":"2410.18050","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","created":"2024-10-23","cited_by_count":49,"area":"rag"},{"id":"2406.00036","title":"EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation","created":"2024-05-27","cited_by_count":17,"area":"rag"},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2504.16429","title":"Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection","created":"2025-04-23","cited_by_count":16,"area":"rag"},{"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":"2402.11573","title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","created":"2024-02-18","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":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"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":"2602.11243","title":"Evaluating Memory Structure in LLM Agents","created":"2026-02-11","cited_by_count":12,"area":"rag"},{"id":"2601.09028","title":"OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG","created":"2026-01-13","cited_by_count":11,"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":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"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":"2505.11271","title":"Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models","created":"2025-05-16","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":"2601.02993","title":"Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation","created":"2026-01-06","cited_by_count":5,"area":"rag"},{"id":"2601.06189","title":"Rational Synthesizers or Heuristic Followers? Analyzing LLMs in RAG-based Question-Answering","created":"2026-01-08","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":"2506.22518","title":"Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation","created":"2025-06-26","cited_by_count":3,"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":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2503.16071","title":"Tuning LLMs by RAG Principles: Towards LLM-native Memory","created":"2025-03-20","cited_by_count":2,"area":"rag"},{"id":"2506.06331","title":"How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG","created":"2025-05-31","cited_by_count":2,"area":"rag"},{"id":"2606.13126","title":"MiniPIC: Flexible Position-Independent Caching in <100LOC","created":"2026-06-11","cited_by_count":2,"area":"rag"},{"id":"2601.06551","title":"L-RAG: Balancing Context and Retrieval with Entropy-Based Lazy Loading","created":"2026-01-10","cited_by_count":1,"area":"rag"},{"id":"2603.07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","created":"2026-03-08","cited_by_count":1,"area":"rag"},{"id":"2604.14339","title":"Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation","created":"2026-04-15","cited_by_count":1,"area":"rag"},{"id":"2606.09441","title":"SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance","created":"2026-06-08","cited_by_count":1,"area":"rag"},{"id":"2606.16494","title":"Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering","created":"2026-06-15","cited_by_count":1,"area":"rag"},{"id":"2605.15913","title":"Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation","created":"2026-05-15","cited_by_count":0,"area":"rag"},{"id":"2607.24554","title":"DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding","created":"2026-07-27","cited_by_count":0,"area":"rag"},{"id":"2609.09768","title":"Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?","created":"2026-09-09","cited_by_count":0,"area":"rag"},{"id":"2609.10372","title":"PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving","created":"2026-09-09","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":"2610.08463","title":"UNREAL: Unifying Retrieval and Long-Context with a Single Model","created":"2026-10-06","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}