{"total":17,"rows":[{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"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":"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":"2512.22195","title":"MatKV: Trading Compute for Flash Storage in LLM Inference","created":"2025-12-20","cited_by_count":2,"area":"rag"},{"id":"2605.18490","title":"Single-Round Vector RAG vs an LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research Corpus","created":"2026-05-18","cited_by_count":2,"area":"rag"},{"id":"2606.04302","title":"LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding","created":"2026-06-03","cited_by_count":2,"area":"rag"},{"id":"2503.05530","title":"Leveraging Approximate Caching for Faster Retrieval-Augmented Generation","created":"2025-03-07","cited_by_count":1,"area":"rag"},{"id":"2503.14103","title":"DangerMaps: Personalized Safety Advice for Travel in Urban Environments using a Retrieval-Augmented Language Model","created":"2025-03-18","cited_by_count":1,"area":"rag"},{"id":"2510.17934","title":"AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM","created":"2025-10-20","cited_by_count":1,"area":"rag"},{"id":"2601.08670","title":"Parallel Context-of-Experts Decoding for Retrieval Augmented Generation","created":"2026-01-13","cited_by_count":1,"area":"rag"},{"id":"2605.27494","title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2501.07523","title":"Parallel Key-Value Cache Fusion for Position Invariant RAG","created":"2025-01-13","cited_by_count":0,"area":"rag"},{"id":"2509.21865","title":"Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding","created":"2025-09-26","cited_by_count":0,"area":"rag"},{"id":"2510.20878","title":"HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement","created":"2025-10-23","cited_by_count":0,"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":"2605.17989","title":"Predictive Prefetching for Retrieval-Augmented Generation","created":"2026-05-18","cited_by_count":0,"area":"rag"},{"id":"2608.07458","title":"CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG","created":"2026-08-07","cited_by_count":0,"area":"rag"}],"next_cursor":null}