{"total":98,"rows":[{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109,"area":"agents"},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"area":"rag"},{"id":"2501.13958","title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models","created":"2025-01-21","cited_by_count":88,"area":"rag"},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2507.07400","title":"KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows","created":"2025-07-10","cited_by_count":56,"area":"agents"},{"id":"2410.15332","title":"EPIC: Efficient Position-Independent Caching for Serving Large Language Models","created":"2024-10-20","cited_by_count":47,"area":null},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"area":null},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2412.03594","title":"BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching","created":"2024-11-29","cited_by_count":32,"area":null},{"id":"2506.14852","title":"Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents","created":"2025-06-17","cited_by_count":27,"area":"agents"},{"id":"2410.03065","title":"Compute Or Load KV Cache? Why Not Both?","created":"2024-10-04","cited_by_count":25,"area":"inference"},{"id":"2505.07203","title":"PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications","created":"2025-05-12","cited_by_count":21,"area":"inference"},{"id":"2409.13761","title":"Do Large Language Models Need a Content Delivery Network?","created":"2024-09-16","cited_by_count":16,"area":"inference"},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2412.11854","title":"Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference","created":"2024-12-16","cited_by_count":15,"area":"rag"},{"id":"2601.22705","title":"CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control","created":"2026-01-30","cited_by_count":14,"area":"inference"},{"id":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2407.15748","title":"MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation","created":"2024-07-22","cited_by_count":8,"area":"rag"},{"id":"2502.01960","title":"MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving","created":"2025-02-04","cited_by_count":8,"area":"mllm"},{"id":"2504.02921","title":"HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse","created":"2025-04-03","cited_by_count":8,"area":"rag"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"id":"2603.04428","title":"Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices","created":"2026-02-17","cited_by_count":8,"area":"agents"},{"id":"2411.13009","title":"LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2606.17034","title":"KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing","created":"2026-06-15","cited_by_count":6,"area":"inference"},{"id":"2606.17107","title":"Models Take Notes at Prefill: KV Cache Can Be Editable and Composable","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2504.14858","title":"Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization","created":"2025-04-21","cited_by_count":5,"area":"lr"},{"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":"2505.12065","title":"Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents","created":"2025-05-17","cited_by_count":5,"area":"agents"},{"id":"2510.18546","title":"EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2602.11550","title":"TS-Memory: Plug-and-Play Memory for Time Series Foundation Models","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2602.21477","title":"Pancake: Hierarchical Memory System for Multi-Agent LLM Serving","created":"2026-02-25","cited_by_count":5,"area":"agents"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2603.23049","title":"PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving","created":"2026-03-24","cited_by_count":4,"area":"rag"},{"id":"2604.10352","title":"ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.06068","title":"VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2410.10859","title":"FAME: Towards Factual Multi-Task Model Editing","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2504.08930","title":"VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG","created":"2025-04-11","cited_by_count":3,"area":"rag"},{"id":"2504.11765","title":"Shared Disk KV Cache Management for Efficient Multi-Instance Inference in RAG-Powered LLMs","created":"2025-04-16","cited_by_count":3,"area":"inference"},{"id":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"id":"2411.00915","title":"Empower Vision Applications with LoRA LMM","created":"2024-11-01","cited_by_count":2,"area":"mllm"},{"id":"2511.12979","title":"RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems","created":"2025-11-17","cited_by_count":2,"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":"2601.08833","title":"Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications","created":"2025-11-14","cited_by_count":2,"area":"inference"},{"id":"2601.21473","title":"ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management","created":"2026-01-29","cited_by_count":2,"area":"agents"},{"id":"2604.08584","title":"CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference","created":"2026-03-30","cited_by_count":2,"area":"inference"},{"id":"2606.04302","title":"LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding","created":"2026-06-03","cited_by_count":2,"area":"rag"},{"id":"2607.17147","title":"SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcri","created":"2026-07-19","cited_by_count":2,"area":"agents"},{"id":"2608.30386","title":"DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2412.10856","title":"RWKV-edge: Deeply Compressed RWKV for Resource-Constrained Devices","created":"2024-12-14","cited_by_count":1,"area":null},{"id":"2501.17802","title":"LEKA:LLM-Enhanced Knowledge Augmentation","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2504.15499","title":"Guillotine: Hypervisors for Isolating Malicious AIs","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2505.10951","title":"SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache","created":"2025-05-16","cited_by_count":1,"area":"rag"},{"id":"2507.14849","title":"Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding","created":"2025-07-20","cited_by_count":1,"area":"lr"},{"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":"2512.08995","title":"PoultryTalk: A Multi-modal Retrieval-Augmented Generation (RAG) System for Intelligent Poultry Management and Decision Support","created":"2025-12-08","cited_by_count":1,"area":"rag"},{"id":"2602.09725","title":"Efficient Remote KV Cache Reuse with GPU-native Video Codec","created":"2026-02-10","cited_by_count":1,"area":"inference"},{"id":"2603.03301","title":"From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.08907","title":"Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.10765","title":"RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems","created":"2026-03-11","cited_by_count":1,"area":"rag"},{"id":"2604.06711","title":"Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.08581","title":"PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design","created":"2026-05-09","cited_by_count":1,"area":"rag"},{"id":"2605.20630","title":"Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"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":"2607.28263","title":"CoMem: Reusing Transformer Depth across Queries with Persistent Intermediate Residuals","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.01718","title":"LaCache: Robust Semantic Caching for LLM Serving","created":"2026-08-03","cited_by_count":1,"area":"inference"},{"id":"2609.10266","title":"KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints","created":"2026-09-09","cited_by_count":1,"area":"inference"},{"id":"2609.39358","title":"Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2508.21307","title":"MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.19670","title":"CoSense-LLM: Semantics at the Edge with Cost- and Uncertainty-Aware Cloud-Edge Cooperation","created":"2025-10-22","cited_by_count":0,"area":"inference"},{"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":"2511.04700","title":"Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation","created":"2025-11-01","cited_by_count":0,"area":"rag"},{"id":"2511.05915","title":"CoEdge-RAG: Optimizing Hierarchical Scheduling for Retrieval-Augmented LLMs in Collaborative Edge Computing","created":"2025-11-08","cited_by_count":0,"area":"rag"},{"id":"2602.18922","title":"Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning","created":"2026-02-21","cited_by_count":0,"area":"agents"},{"id":"2604.20452","title":"HaS: Accelerating RAG through Homology-Aware Speculative Retrieval","created":"2026-04-22","cited_by_count":0,"area":"rag"},{"id":"2604.26176","title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering","created":"2026-04-28","cited_by_count":0,"area":"rag"},{"id":"2605.18226","title":"Context Memorization for Efficient Long Context Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.13097","title":"Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2606.14779","title":"Unified KV Pooling to Accelerate Long-Context LLM Serving","created":"2026-06-10","cited_by_count":0,"area":"inference"},{"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"},{"id":"2606.21238","title":"Recency/Frequency Adaptive KV Caching for Large Language Model Serving","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.02525","title":"PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving","created":"2026-05-10","cited_by_count":0,"area":"inference"},{"id":"2607.22319","title":"Towards Trustworthy and Cost-Efficient Data Integration: From Na\\\"ive RAG to Agentic RAG","created":"2026-07-24","cited_by_count":0,"area":"agents"},{"id":"2607.23838","title":"TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation","created":"2026-07-26","cited_by_count":0,"area":"rag"},{"id":"2607.24260","title":"KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems","created":"2026-07-27","cited_by_count":0,"area":"inference"},{"id":"2608.06007","title":"TensorCast: The Missing Tensor Management Layer in Large Language Model Infrastructure","created":"2026-08-06","cited_by_count":0,"area":"inference"},{"id":"2609.05760","title":"RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.11209","title":"REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.16215","title":"Where Should the KV Cache Live? Placement Policies Across GPU, CPU, and SSD for Long-Lived Sessions","created":"2026-09-14","cited_by_count":0,"area":"inference"},{"id":"2609.26828","title":"Bridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02839","title":"To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}