CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion

arXiv:2609.35139 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

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

Sources

• KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
• The Llama 3 Herd of Models
• EPIC: Efficient Position-Independent Caching for Serving Large Language Models
• TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
• Qwen2.5 Technical Report
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• Chain-of-Retrieval Augmented Generation
• CacheClip: Accelerating RAG with Effective KV Cache Reuse
• APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
• CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks