# ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models

arXiv: https://arxiv.org/abs/2510.01290 · HTML: https://mlsanity.com/paper/2510.01290/

## Key facts

- Cited by 21 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 50 of its 76 references that are in the map.
- First posted on arXiv 1 Oct 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, 30 of 50)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [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)
- [Compressed Chain of Thought: Efficient Reasoning Through Dense Representations](https://mlsanity.com/paper/2412.13171/) (2024)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference](https://mlsanity.com/paper/2410.21465/) (2024)
- [Thought Anchors: Which LLM Reasoning Steps Matter?](https://mlsanity.com/paper/2506.19143/) (2025)
- [Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://mlsanity.com/paper/2503.05179/) (2025)
- [Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference](https://mlsanity.com/paper/2403.09636/) (2024)
- [SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs](https://mlsanity.com/paper/2502.12134/) (2025)
- [LightThinker: Thinking Step-by-Step Compression](https://mlsanity.com/paper/2502.15589/) (2025)
- [Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning](https://mlsanity.com/paper/2410.19258/) (2024)
- [Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks](https://mlsanity.com/paper/2407.08454/) (2024)
- [KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction](https://mlsanity.com/paper/2505.23416/) (2025)
- [Understanding Reasoning in Thinking Language Models via Steering Vectors](https://mlsanity.com/paper/2506.18167/) (2025)

## Built on by (most cited first, 21 of 21)

- [MEMENTO: Teaching LLMs to Manage Their Own Context](https://mlsanity.com/paper/2604.09852/) (2026)
- [SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning](https://mlsanity.com/paper/2602.22603/) (2026)
- [OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization](https://mlsanity.com/paper/2605.17757/) (2026)
- [SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models](https://mlsanity.com/paper/2512.07993/) (2025)
- [ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning](https://mlsanity.com/paper/2605.22106/) (2026)
- [TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks](https://mlsanity.com/paper/2605.17170/) (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)
- [Prefix Sliding for efficient test-time scaling](https://mlsanity.com/paper/2608.26070/) (2026)
- [Adaptive Mass-Segmented KV Compression for Long-Context Reasoning](https://mlsanity.com/paper/2605.23200/) (2026)
- [Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs](https://mlsanity.com/paper/2607.14107/) (2026)
- [Language Models Can Control Their Own Attention](https://mlsanity.com/paper/2609.02737/) (2026)
- [Monte Carlo Estimation for KV Cache Eviction](https://mlsanity.com/paper/2610.07643/) (2026)
- [State commitment learning: training language models to distinguish computation from memory](https://mlsanity.com/paper/2606.05201/) (2026)
- [Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2608.21265/) (2026)
- [GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving](https://mlsanity.com/paper/2609.03494/) (2026)
- [StepKV: Step-Aware KV Cache Compression for LLM Agents](https://mlsanity.com/paper/2609.22158/) (2026)
- [ActKV: Efficient LLM Agents through Action-Guided KV Cache Management](https://mlsanity.com/paper/2609.31395/) (2026)
- [Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving](https://mlsanity.com/paper/2609.33536/) (2026)
- [WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds](https://mlsanity.com/paper/2610.02713/) (2026)
- [Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning](https://mlsanity.com/paper/2610.05685/) (2026)

## Abstract (arXiv)

The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (KV) cache, quickly overwhelming GPU memory. To address this challenge, we propose ThinKV, a thought-adaptive KV cache compression framework. ThinKV is based on the observation that attention sparsity reveals distinct thought types with varying importance within the CoT. It applies a hybrid quantization-eviction strategy, assigning token precision by thought importance and progressively evicting tokens from less critical thoughts as reasoning trajectories evolve. Furthermore, to implement ThinKV, we design a kernel that extends PagedAttention to enable efficient reuse of evicted tokens' memory slots, eliminating compaction overheads. Extensive experiments on DeepSeek-R1-Distill, GPT-OSS, and NVIDIA AceReason across mathematics and coding benchmarks show that ThinKV achieves near-lossless accuracy with less than 5% of the original KV cache, while improving performance with up to 5.8x higher inference throughput over state-of-the-art baselines.