Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
Westlake University（西华大学）；McGill University（麦吉尔大学）；Mila - Quebec AI Institute（魁北克AI研究院）；Zhejiang University（浙江大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德智能大学）
Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information loss during decoding, creating critical challenges for KV cache compression. Existing token-dropping methods directly disrupt reasoning chains by removing intermediate steps, while head-reallocation methods, designed for retrieval tasks, fail to preserve the heads essential for generative reasoning. However, no existing method can identify which attention heads genuinely maintain reasoning consistency and control generation termination. To address this, we propose RLKV, which uses reinforcement learning as a probe to discover which heads contribute to reasoning quality by directly optimizing their cache usage against actual generation outcomes. This discovery naturally leads to an efficient compression strategy: we allocate full KV cache to reasoning-critical heads while aggressively compressing others with constant-size KV cache. Experiments reveal that a fraction of heads proves essential for reasoning, enabling 20--60% cache reduction with near-lossless performance across diverse tasks and models, and up to 2.06x end-to-end speedup at 60% reduction.
VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization
LUMIA Lab（LUMIA实验室）；School of Artificial Intelligence（人工智能学院）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Cambridge（剑桥大学）；National University of Singapore（新加坡国立大学）
SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
School of Computer Science and Technology, University of Science and Technology of China（计算机科学与技术学院，科学技术大学）；Suzhou Institute for Advanced Research, University of Science and Technology of China（苏州先进研究院，科学技术大学）
DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression
University of Electronic Science and Technology of China（电子科技大学）；Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province（四川省泛在智能与可信服务重点实验室）
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；CSE, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系）；Guangzhou HKUST Fok Ying Tung Research Institute（广州HKUST福 Ying Tung研究 institute）；Terminus Technologies
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机学院）；Xiaomi Inc.（小米公司）
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
University of Wisconsin - Madison（威斯康星大学麦迪逊分校）；Microsoft（微软）；Carnegie Mellon University（卡内基梅隆大学）；California Institute of Technology（加州理工学院）；University of California - San Diego（加州大学圣地亚哥分校）；University of Surrey（萨里大学）；University of California - Berkeley（加州大学伯克利分校）
EvolKV: Evolutionary KV Cache Compression for LLM Inference
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学先进交叉学科学院）；The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, CAS（复杂系统认知与决策智能重点实验室）；ETH Zurich（苏黎世联邦理工学院）
AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（脑启发智能感知与认知联合实验室，中国科学技术大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）
ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
Information Hub, The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学信息中心）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
University of Wisconsin - Madison（威斯康星大学麦迪逊分校）；Peking University（北京大学）；Nanjing University（南京大学）；University of Surrey（Surrey 大学）；Qwen（通义实验室）；University of California - Riverside（加州大学河滨分校）；Microsoft（微软公司）
xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
Cornell University（康奈尔大学）；University of Washington（华盛顿大学）；Department of Computer Science, National Yang Ming Chiao Tung University（国立阳明交通大学计算机科学系）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Surrey（塞夫顿大学）；Microsoft Research Asia（微软亚洲研究院）
