{"total":268,"rows":[{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"area":null},{"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":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257,"area":"lr"},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"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":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"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":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109,"area":"agents"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2407.00023","title":"Preble: Efficient Distributed Prompt Scheduling for LLM Serving","created":"2024-05-08","cited_by_count":70,"area":"inference"},{"id":"2406.17565","title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool","created":"2024-06-25","cited_by_count":68,"area":"inference"},{"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":"2312.05516","title":"Stateful Large Language Model Serving with Pensieve","created":"2023-12-09","cited_by_count":61,"area":"inference"},{"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":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58,"area":null},{"id":"2407.21439","title":"MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training","created":"2024-07-31","cited_by_count":50,"area":"mllm"},{"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":"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":"2510.12872","title":"KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems","created":"2025-10-14","cited_by_count":40,"area":"agents"},{"id":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37,"area":"rag"},{"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":"2411.00142","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","created":"2024-10-31","cited_by_count":34,"area":"lr"},{"id":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"id":"2503.08311","title":"Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference","created":"2025-03-11","cited_by_count":33,"area":null},{"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":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"area":null},{"id":"2408.08147","title":"P/D-Serve: Serving Disaggregated Large Language Model at Scale","created":"2024-08-15","cited_by_count":27,"area":"inference"},{"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":"2508.18572","title":"Strata: Hierarchical Context Caching for Long Context Language Model Serving","created":"2025-08-26","cited_by_count":26,"area":"inference"},{"id":"2410.03065","title":"Compute Or Load KV Cache? Why Not Both?","created":"2024-10-04","cited_by_count":25,"area":"inference"},{"id":"2412.04036","title":"SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions","created":"2024-12-05","cited_by_count":25,"area":null},{"id":"2312.14950","title":"TypeFly: Flying Drones with Large Language Model","created":"2023-12-08","cited_by_count":23,"area":null},{"id":"2403.05821","title":"Optimizing LLM Queries in Relational Data Analytics Workloads","created":"2024-03-09","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2412.15238","title":"Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks","created":"2024-12-12","cited_by_count":22,"area":"lr"},{"id":"2503.16525","title":"KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse","created":"2025-03-17","cited_by_count":22,"area":"inference"},{"id":"2502.07776","title":"Auditing Prompt Caching in Language Model APIs","created":"2025-02-11","cited_by_count":20,"area":null},{"id":"2510.08790","title":"COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2404.00242","title":"DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference","created":"2024-03-30","cited_by_count":19,"area":"inference"},{"id":"2601.06007","title":"Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks","created":"2026-01-09","cited_by_count":19,"area":"agents"},{"id":"2510.03346","title":"KVComm: Enabling Efficient LLM Communication through Selective KV Sharing","created":"2025-10-02","cited_by_count":18,"area":null},{"id":"2412.10543","title":"METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation","created":"2024-12-13","cited_by_count":17,"area":"rag"},{"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":"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":"2606.30560","title":"TraceLab: Characterizing Coding Agent Workloads for LLM Serving","created":"2026-06-29","cited_by_count":16,"area":"agents"},{"id":"2404.06910","title":"Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation","created":"2024-04-10","cited_by_count":15,"area":"rag"},{"id":"2407.15309","title":"vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving","created":"2024-07-22","cited_by_count":15,"area":"inference"},{"id":"2603.04814","title":"Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents","created":"2026-03-05","cited_by_count":15,"area":"agents"},{"id":"2608.03893","title":"Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse","created":"2026-08-04","cited_by_count":15,"area":"inference"},{"id":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"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":"2402.14808","title":"RelayAttention for Efficient Large Language Model Serving with Long System Prompts","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2508.07675","title":"Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation","created":"2025-08-11","cited_by_count":13,"area":"inference"},{"id":"2410.05265","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2505.01658","title":"A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency","created":"2025-05-03","cited_by_count":12,"area":null},{"id":"2512.16822","title":"MEPIC: Memory Efficient Position Independent Caching for LLM Serving","created":"2025-12-18","cited_by_count":11,"area":"rag"},{"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":"2510.02758","title":"TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling","created":"2025-10-03","cited_by_count":10,"area":"inference"},{"id":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2512.16391","title":"Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference","created":"2025-12-18","cited_by_count":10,"area":"lr"},{"id":"2604.13226","title":"KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs","created":"2026-04-14","cited_by_count":10,"area":null},{"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":"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":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"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":"2603.13281","title":"ICaRus: Identical Cache Reuse for Efficient Multi Model Inference","created":"2026-02-27","cited_by_count":8,"area":"agents"},{"id":"2603.13289","title":"RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse","created":"2026-02-28","cited_by_count":8,"area":"agents"},{"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":"2403.14919","title":"Hierarchical Skip Decoding for Efficient Autoregressive Text Generation","created":"2024-03-22","cited_by_count":7,"area":"inference"},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2606.06256","title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","created":"2026-06-04","cited_by_count":7,"area":"inference"},{"id":"2606.20537","title":"Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving","created":"2026-06-18","cited_by_count":7,"area":"inference"},{"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":"2402.15943","title":"Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","created":"2024-02-25","cited_by_count":6,"area":null},{"id":"2404.10552","title":"Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2506.07334","title":"Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models","created":"2025-06-09","cited_by_count":6,"area":"inference"},{"id":"2509.02121","title":"Batch Query Processing and Optimization for Agentic Workflows","created":"2025-09-02","cited_by_count":6,"area":"inference"},{"id":"2509.24832","title":"SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2602.01519","title":"You Need an Encoder for Native Position-Independent Caching","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2605.00528","title":"SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"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":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2404.03353","title":"Towards Pareto Optimal Throughput in Small Language Model Serving","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2501.04012","title":"FlexCache: Flexible Approximate Cache System for Video Diffusion","created":"2024-12-18","cited_by_count":5,"area":"diffusion"},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2505.03756","title":"Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management","created":"2025-04-19","cited_by_count":5,"area":"inference"},{"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":"2510.10138","title":"Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task","created":"2025-10-11","cited_by_count":5,"area":null}],"next_cursor":"100"}