{"total":245,"rows":[{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398,"area":"agents"},{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"area":"inference"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126,"area":"inference"},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"area":null},{"id":"2410.23317","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","created":"2024-10-29","cited_by_count":43,"area":"mllm"},{"id":"2502.14051","title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression","created":"2025-02-19","cited_by_count":41,"area":"inference"},{"id":"2506.02634","title":"KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider","created":"2025-06-03","cited_by_count":41,"area":"inference"},{"id":"2410.22134","title":"ProMoE: Fast MoE-based LLM Serving using Proactive Caching","created":"2024-10-29","cited_by_count":40,"area":"moe"},{"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":"2411.02886","title":"TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection","created":"2024-11-05","cited_by_count":39,"area":"inference"},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2508.01875","title":"StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding","created":"2025-08-03","cited_by_count":33,"area":"inference"},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29,"area":"inference"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"id":"2502.05370","title":"Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading","created":"2025-02-07","cited_by_count":24,"area":"moe"},{"id":"2412.13649","title":"SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation","created":"2024-12-18","cited_by_count":20,"area":"inference"},{"id":"2503.08879","title":"LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference","created":"2025-03-11","cited_by_count":20,"area":"inference"},{"id":"2409.04992","title":"InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference","created":"2024-09-08","cited_by_count":19,"area":"inference"},{"id":"2510.03346","title":"KVComm: Enabling Efficient LLM Communication through Selective KV Sharing","created":"2025-10-02","cited_by_count":18,"area":null},{"id":"2504.20068","title":"JITServe: SLO-aware LLM Serving with Imprecise Request Information","created":"2025-04-24","cited_by_count":17,"area":"inference"},{"id":"2507.08143","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","created":"2025-07-10","cited_by_count":17,"area":"inference"},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16,"area":"inference"},{"id":"2504.19720","title":"Taming the Titans: A Survey of Efficient LLM Inference Serving","created":"2025-04-28","cited_by_count":16,"area":"inference"},{"id":"2510.18586","title":"TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications","created":"2025-10-21","cited_by_count":16,"area":"inference"},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2502.15524","title":"HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds","created":"2025-02-21","cited_by_count":14,"area":"inference"},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14,"area":"safety"},{"id":"2505.13109","title":"FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference","created":"2025-05-19","cited_by_count":14,"area":"inference"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2411.17089","title":"KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation","created":"2024-11-26","cited_by_count":13,"area":"inference"},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"id":"2502.12224","title":"Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate","created":"2025-02-17","cited_by_count":13,"area":"moe"},{"id":"2505.02922","title":"RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference","created":"2025-05-05","cited_by_count":13,"area":"inference"},{"id":"2508.06447","title":"SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning","created":"2025-08-08","cited_by_count":13,"area":"inference"},{"id":"2602.11243","title":"Evaluating Memory Structure in LLM Agents","created":"2026-02-11","cited_by_count":12,"area":"rag"},{"id":"2410.00531","title":"TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices","created":"2024-10-01","cited_by_count":11,"area":null},{"id":"2507.01438","title":"EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices","created":"2025-07-02","cited_by_count":11,"area":"inference"},{"id":"2511.20172","title":"Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management","created":"2025-11-25","cited_by_count":11,"area":"inference"},{"id":"2603.16104","title":"Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective","created":"2026-03-17","cited_by_count":11,"area":"agents"},{"id":"2501.14808","title":"HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location","created":"2025-01-15","cited_by_count":10,"area":"inference"},{"id":"2505.19586","title":"TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization","created":"2025-05-26","cited_by_count":10,"area":"inference"},{"id":"2507.09019","title":"On Evaluating Performance of LLM Inference Serving Systems","created":"2025-07-11","cited_by_count":10,"area":"inference"},{"id":"2606.16824","title":"CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents","created":"2026-06-15","cited_by_count":10,"area":"inference"},{"id":"2502.12574","title":"HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading","created":"2025-02-18","cited_by_count":9,"area":"inference"},{"id":"2503.15921","title":"SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models","created":"2025-03-20","cited_by_count":9,"area":"inference"},{"id":"2505.09142","title":"ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor","created":"2025-05-14","cited_by_count":9,"area":"inference"},{"id":"2510.11938","title":"FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters","created":"2025-10-13","cited_by_count":9,"area":"inference"},{"id":"2602.23036","title":"LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure","created":"2026-02-26","cited_by_count":9,"area":"inference"},{"id":"2501.06709","title":"Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management","created":"2025-01-12","cited_by_count":8,"area":"inference"},{"id":"2509.23638","title":"LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers","created":"2025-09-28","cited_by_count":8,"area":"moe"},{"id":"2511.20714","title":"Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation","created":"2025-11-25","cited_by_count":8,"area":"wm"},{"id":"2602.06502","title":"DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving","created":"2026-02-06","cited_by_count":8,"area":"inference"},{"id":"2604.03143","title":"TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing","created":"2026-04-03","cited_by_count":8,"area":"inference"},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2502.04077","title":"AttentionPredictor: Temporal Patterns Matter for KV Cache Compression","created":"2025-02-06","cited_by_count":7,"area":"inference"},{"id":"2503.00392","title":"Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving","created":"2025-03-01","cited_by_count":7,"area":"inference"},{"id":"2505.22913","title":"Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference","created":"2025-05-28","cited_by_count":7,"area":"inference"},{"id":"2506.02572","title":"HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference","created":"2025-06-03","cited_by_count":7,"area":"inference"},{"id":"2508.02751","title":"SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference","created":"2025-08-03","cited_by_count":6,"area":"inference"},{"id":"2509.24626","title":"SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2601.10729","title":"OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration","created":"2026-01-05","cited_by_count":6,"area":"inference"},{"id":"2504.14775","title":"gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling","created":"2025-04-21","cited_by_count":5,"area":"inference"},{"id":"2506.06644","title":"Spark Transformer: Reactivating Sparsity in FFN and Attention","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2506.08018","title":"KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache","created":"2025-05-18","cited_by_count":5,"area":"inference"},{"id":"2510.15312","title":"Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution","created":"2025-10-17","cited_by_count":5,"area":"rag"},{"id":"2510.16040","title":"Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing","created":"2025-10-16","cited_by_count":5,"area":"inference"},{"id":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"id":"2512.09472","title":"WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving","created":"2025-12-10","cited_by_count":5,"area":"inference"},{"id":"2512.12284","title":"V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval","created":"2025-12-13","cited_by_count":5,"area":"inference"},{"id":"2601.21709","title":"Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis","created":"2026-01-29","cited_by_count":5,"area":"inference"},{"id":"2602.05362","title":"Imagine a City: CityGenAgent for Procedural 3D City Generation","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2604.10539","title":"IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs","created":"2026-04-12","cited_by_count":5,"area":"inference"},{"id":"2605.18071","title":"KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference","created":"2026-05-18","cited_by_count":5,"area":"inference"},{"id":"2606.04511","title":"SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference","created":"2026-06-03","cited_by_count":5,"area":null},{"id":"2502.09921","title":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","created":"2025-02-14","cited_by_count":4,"area":"inference"},{"id":"2504.08378","title":"Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2507.03153","title":"HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2507.17133","title":"BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs","created":"2025-07-23","cited_by_count":4,"area":"moe"},{"id":"2508.06041","title":"DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment","created":"2025-08-08","cited_by_count":4,"area":null},{"id":"2510.06175","title":"VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization","created":"2025-10-07","cited_by_count":4,"area":"inference"},{"id":"2510.11292","title":"LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences","created":"2025-10-13","cited_by_count":4,"area":"inference"},{"id":"2510.23649","title":"Efficient Low Rank Attention for Long-Context Inference in Large Language Models","created":"2025-10-25","cited_by_count":4,"area":null},{"id":"2511.00321","title":"Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits","created":"2025-10-31","cited_by_count":4,"area":"inference"},{"id":"2512.07647","title":"A Mathematical Theory of Top-$k$ Sparse Attention via Total Variation Distance","created":"2025-12-08","cited_by_count":4,"area":null},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2603.22910","title":"EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction","created":"2026-03-24","cited_by_count":4,"area":"inference"}],"next_cursor":"100"}