# R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

arXiv: https://arxiv.org/abs/2505.24133 · HTML: https://mlsanity.com/paper/2505.24133/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

## Builds on (most cited first, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference](https://mlsanity.com/paper/2410.21465/) (2024)
- [Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference](https://mlsanity.com/paper/2403.09636/) (2024)
- [Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning](https://mlsanity.com/paper/2410.19258/) (2024)
- [Concise Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2504.05185/) (2025)
- [Eigen Attention: Attention in Low-Rank Space for KV Cache Compression](https://mlsanity.com/paper/2408.05646/) (2024)
- [WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More](https://mlsanity.com/paper/2402.12065/) (2024)
- [LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy](https://mlsanity.com/paper/2410.03111/) (2024)
- [Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2502.13260/) (2025)
- [Compressed Context Memory For Online Language Model Interaction](https://mlsanity.com/paper/2312.03414/) (2023)
- [Think When You Need: Self-Adaptive Chain-of-Thought Learning](https://mlsanity.com/paper/2504.03234/) (2025)
- [Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models](https://mlsanity.com/paper/2504.13626/) (2025)
- [Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning](https://mlsanity.com/paper/2503.15952/) (2025)

## Built on by (most cited first, 30 of 54)

- [SeerAttention-R: Sparse Attention Adaptation for Long Reasoning](https://mlsanity.com/paper/2506.08889/) (2025)
- [ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models](https://mlsanity.com/paper/2510.01290/) (2025)
- [TriAttention: Efficient Long Reasoning with Trigonometric KV Compression](https://mlsanity.com/paper/2604.04921/) (2026)
- [MEMENTO: Teaching LLMs to Manage Their Own Context](https://mlsanity.com/paper/2604.09852/) (2026)
- [WorldKV: Efficient World Memory with World Retrieval and Compression](https://mlsanity.com/paper/2605.22718/) (2026)
- [SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning](https://mlsanity.com/paper/2602.22603/) (2026)
- [Which Heads Matter for Reasoning? RL-Guided KV Cache Compression](https://mlsanity.com/paper/2510.08525/) (2025)
- [KaVa: Latent Reasoning via Compressed KV-Cache Distillation](https://mlsanity.com/paper/2510.02312/) (2025)
- [Value-Aware Stochastic KV Cache Eviction for Reasoning Models](https://mlsanity.com/paper/2606.03928/) (2026)
- [DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2510.09883/) (2025)
- [LongFlow: Efficient KV Cache Compression for Reasoning Models](https://mlsanity.com/paper/2603.11504/) (2026)
- [FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning](https://mlsanity.com/paper/2601.19001/) (2026)
- [When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression](https://mlsanity.com/paper/2605.08234/) (2026)
- [Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models](https://mlsanity.com/paper/2510.10964/) (2025)
- [KV Admission: Learning What to Write for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2512.17452/) (2025)
- [DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention](https://mlsanity.com/paper/2605.18753/) (2026)
- [MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression](https://mlsanity.com/paper/2604.17695/) (2026)
- [Epiphany-Aware KV Cache Eviction Without the Attention Matrix](https://mlsanity.com/paper/2606.26472/) (2026)
- [KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression](https://mlsanity.com/paper/2607.01237/) (2026)
- [Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression](https://mlsanity.com/paper/2608.01631/) (2026)
- [KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving](https://mlsanity.com/paper/2608.15797/) (2026)
- [Prefix Sliding for efficient test-time scaling](https://mlsanity.com/paper/2608.26070/) (2026)
- [SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking](https://mlsanity.com/paper/2609.13141/) (2026)
- [Transactional Attention: Semantic Sponsorship for KV-Cache Retention](https://mlsanity.com/paper/2604.11288/) (2026)
- [CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration](https://mlsanity.com/paper/2604.25080/) (2026)
- [AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees](https://mlsanity.com/paper/2605.19260/) (2026)
- [Adaptive Mass-Segmented KV Compression for Long-Context Reasoning](https://mlsanity.com/paper/2605.23200/) (2026)
- [DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression](https://mlsanity.com/paper/2607.06523/) (2026)
- [LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding](https://mlsanity.com/paper/2607.24555/) (2026)
- [Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning](https://mlsanity.com/paper/2609.03430/) (2026)

## Abstract (arXiv)

Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohibitively large key-value (KV) caches during inference. While chain-of-thought inference significantly improves performance on complex reasoning tasks, it can also lead to reasoning failures when deployed with existing KV cache compression approaches. To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models. Our method preserves nearly 100% of the full KV cache performance using only 10% of the KV cache, substantially outperforming existing KV cache baselines, which reach only 60% of the performance. Remarkably, R-KV even achieves 105% of full KV cache performance with 16% of the KV cache. This KV-cache reduction also leads to a 90% memory saving and a 6.6X throughput over standard chain-of-thought reasoning inference. Experimental results show that R-KV consistently outperforms existing KV cache compression baselines across two mathematical reasoning datasets.