{"total":66,"rows":[{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61,"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":"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":"2603.18897","title":"Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving","created":"2026-03-19","cited_by_count":20,"area":"agents"},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2512.16822","title":"MEPIC: Memory Efficient Position Independent Caching for LLM Serving","created":"2025-12-18","cited_by_count":11,"area":"rag"},{"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":"2602.01053","title":"LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents","created":"2026-02-01","cited_by_count":10,"area":"agents"},{"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":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"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":"2603.13289","title":"RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse","created":"2026-02-28","cited_by_count":8,"area":"agents"},{"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":"2602.01519","title":"You Need an Encoder for Native Position-Independent Caching","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2604.20920","title":"Simplified Sparse Attention via Gist Tokens","created":"2026-04-22","cited_by_count":6,"area":"inference"},{"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":"2504.01281","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":"2601.12904","title":"From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":5,"area":"rag"},{"id":"2602.10377","title":"Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs","created":"2026-02-10","cited_by_count":5,"area":"vla"},{"id":"2603.20218","title":"An experimental study of KV cache reuse strategies in chunk-level caching systems","created":"2026-03-03","cited_by_count":5,"area":"rag"},{"id":"2605.19932","title":"PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents","created":"2026-05-19","cited_by_count":4,"area":"agents"},{"id":"2607.17715","title":"C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference","created":"2026-07-20","cited_by_count":4,"area":"rag"},{"id":"2607.28979","title":"KV Cache Translation across Heterogeneous Large Language Models","created":"2026-07-31","cited_by_count":4,"area":"inference"},{"id":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2602.10986","title":"TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents","created":"2026-02-11","cited_by_count":3,"area":"agents"},{"id":"2603.05353","title":"InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context","created":"2026-03-05","cited_by_count":3,"area":"rag"},{"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":"2606.23581","title":"Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse","created":"2026-06-22","cited_by_count":3,"area":"inference"},{"id":"2608.11231","title":"LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs","created":"2026-07-31","cited_by_count":3,"area":"inference"},{"id":"2608.19662","title":"ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2601.08343","title":"When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges","created":"2026-01-13","cited_by_count":2,"area":"agents"},{"id":"2601.08743","title":"TableCache: Primary Foreign Key Guided KV Cache Precomputation for Low Latency Text-to-SQL","created":"2026-01-13","cited_by_count":2,"area":"inference"},{"id":"2607.19957","title":"HijackKV: New Threat in Position-Independent KV Cache Reuse","created":"2026-07-22","cited_by_count":2,"area":"inference"},{"id":"2607.23693","title":"Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV","created":"2026-07-26","cited_by_count":2,"area":"inference"},{"id":"2607.28069","title":"SemPIC: Learning Semantic Position-Independent KV Caches","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2601.03067","title":"Joint Encoding of KV-Cache Blocks for Scalable LLM Serving","created":"2026-01-06","cited_by_count":1,"area":"inference"},{"id":"2601.08670","title":"Parallel Context-of-Experts Decoding for Retrieval Augmented Generation","created":"2026-01-13","cited_by_count":1,"area":"rag"},{"id":"2602.11688","title":"GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving","created":"2026-02-12","cited_by_count":1,"area":"inference"},{"id":"2606.09441","title":"SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance","created":"2026-06-08","cited_by_count":1,"area":"rag"},{"id":"2609.10266","title":"KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints","created":"2026-09-09","cited_by_count":1,"area":"inference"},{"id":"2510.01239","title":"CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.08774","title":"Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings","created":"2025-10-09","cited_by_count":0,"area":null},{"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":"2604.14159","title":"HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.16864","title":"HieraSparse: Hierarchical Semi-Structured Sparse KV Attention","created":"2026-04-18","cited_by_count":0,"area":"inference"},{"id":"2606.14672","title":"Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2607.19547","title":"ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"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"},{"id":"2608.11218","title":"MaSRead: Content-Addressed Reading of Replicated Latent Stores","created":"2026-07-21","cited_by_count":0,"area":"inference"},{"id":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.09768","title":"Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?","created":"2026-09-09","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":"2609.17346","title":"Where Should a Document Live: Context, Representations, or Parameters?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.31415","title":"Evaluating the accuracy of KV cache reuse techniques","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.33503","title":"RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse","created":"2026-09-27","cited_by_count":0,"area":"rag"},{"id":"2609.33759","title":"Positions Are Not Facts: The Mismatch Between KV Caches and Memory","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.34060","title":"KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.35139","title":"CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion","created":"2026-09-28","cited_by_count":0,"area":"rag"},{"id":"2609.36722","title":"ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.05833","title":"Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.08820","title":"Task-Oriented Key-Layer KV Communication for Efficient Latent Multi-Agent Collaboration","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.13060","title":"KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse","created":"2026-10-09","cited_by_count":0,"area":"inference"},{"id":"2610.15095","title":"Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.15186","title":"SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG","created":"2026-10-10","cited_by_count":0,"area":"rag"},{"id":"2610.18861","title":"Hybrid Reasoning Agents","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}