{"total":17,"rows":[{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119,"area":"rag"},{"id":"2310.15556","title":"TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction","created":"2023-10-24","cited_by_count":34,"area":"rag"},{"id":"2410.20299","title":"EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update","created":"2024-10-27","cited_by_count":2,"area":"rag"},{"id":"2508.13828","title":"Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration","created":"2025-08-19","cited_by_count":2,"area":"rag"},{"id":"2601.02917","title":"RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems","created":"2026-01-06","cited_by_count":2,"area":"rag"},{"id":"2604.00053","title":"The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products","created":"2026-03-31","cited_by_count":2,"area":"rag"},{"id":"2604.03455","title":"Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench","created":"2026-04-03","cited_by_count":2,"area":"rag"},{"id":"2307.05915","title":"Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering","created":"2023-07-12","cited_by_count":1,"area":"rag"},{"id":"2607.12188","title":"Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems","created":"2026-07-13","cited_by_count":1,"area":"rag"},{"id":"2609.30087","title":"Return or Revise? Learning When Revision Helps Retrieval-Augmented QA","created":"2026-09-24","cited_by_count":1,"area":"rag"},{"id":"2501.07793","title":"Unsupervised Query Routing for Retrieval Augmented Generation","created":"2025-01-14","cited_by_count":0,"area":"rag"},{"id":"2511.16681","title":"SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases","created":"2025-11-12","cited_by_count":0,"area":"rag"},{"id":"2601.00841","title":"SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes","created":"2025-12-27","cited_by_count":0,"area":"rag"},{"id":"2606.11907","title":"Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation","created":"2026-06-10","cited_by_count":0,"area":"rag"},{"id":"2608.21792","title":"HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries","created":"2026-08-22","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"}],"next_cursor":null}