# Information-Aware KV Cache Compression for Long Reasoning

arXiv: https://arxiv.org/abs/2606.26875 · HTML: https://mlsanity.com/paper/2606.26875/

## Key facts

- Cited by 2 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 14 of its 22 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## 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 / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks](https://mlsanity.com/paper/2407.08454/) (2024)
- [Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution](https://mlsanity.com/paper/2510.00636/) (2025)
- [LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion](https://mlsanity.com/paper/2501.15089/) (2025)
- [D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models](https://mlsanity.com/paper/2406.13035/) (2024)
- [Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning](https://mlsanity.com/paper/2505.13866/) (2025)
- [SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully](https://mlsanity.com/paper/2401.05930/) (2024)
- [FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration](https://mlsanity.com/paper/2502.01068/) (2025)
- [FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension](https://mlsanity.com/paper/2505.00570/) (2025)
- [SeLaR: Selective Latent Reasoning in Large Language Models](https://mlsanity.com/paper/2604.08299/) (2026)

## Built on by (most cited first, 2 of 2)

- [GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving](https://mlsanity.com/paper/2609.03494/) (2026)
- [Divergence Timing and Cumulative Disagreement under KV-Cache Eviction](https://mlsanity.com/paper/2609.16617/) (2026)

## Abstract (arXiv)

Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages. Existing KV cache compression methods mainly rely on attention weights to estimate token importance. While attention effectively captures contextual relevance, it overlooks complementary information-theoretic signals related to predictive uncertainty and token informativeness. In this paper, we revisit token importance from a forward-looking perspective and introduce textitForward Influence, a metric that measures how compressed tokens affect future contexts. Our analysis reveals that tokens selected by attention scores mainly influence nearby contexts, whereas tokens associated with high predictive uncertainty exhibit substantially stronger influence on distant future contexts. Based on the observation, we propose InfoKV, an entropy-aware KV cache compression framework that incorporates information-theoretic signals. It combines token-level predictive uncertainty with layer-wise representation evolution and integrates the resulting entropy scores with attention scores during reasoning. Experiments on long-context reasoning benchmarks with Llama-3.1, Llama-3.2, and DeepSeek-R1 demonstrate that InfoKV consistently outperforms existing attention-based KV compression methods in both long prefilling and decoding scenarios.