KV squared: A Self-Refining KV Cache

arXiv:2610.03198 · cs.AI, cs.CL · Submitted 2026-10-02 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-02

Updated: 2026-10-15

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• KV cache — 1× in this paper · explained in 3 episodes

Sources

• InferCept: Efficient Intercept Support for Augmented Large Language Model Inference
• Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
• Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention
• Lost in the Middle: How Language Models Use Long Contexts
• Preble: Efficient Distributed Prompt Scheduling for LLM Serving
• No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems