ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation
cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/Infini-AI-Lab/APE4https:
Terminology
Sources
- UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
- Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
- A Survey of Context Engineering for Large Language Models
- A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
- From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
- Deep Tabular Research via Continual Experience-Driven Execution
- Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning
- Skill Retrieval Augmentation for Agentic AI
- You Need an Encoder for Native Position-Independent Caching
- SemPIC: Learning Semantic Position-Independent KV Caches
- $A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving
- CacheClip: Accelerating RAG with Effective KV Cache Reuse
- KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse
- RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
- AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
- Models Take Notes at Prefill: KV Cache Can Be Editable and Composable
- MEPIC: Memory Efficient Position Independent Caching for LLM Serving
- MiniPIC: Flexible Position-Independent Caching in <100LOC
- MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving
- VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering