CASK: Core-Aware Selective KV Compression for Reasoning Traces
In large language models performing long-form reasoning, the KV cache grows rapidly with decode length, creating bottlenecks in memory and inference stability. Existing reasoning-oriented KV compression has mostly followed an eviction-centered view: estimate token importance more accurately, then discard lower-ranked entries. Our analysis suggests that scorer refinement alone often fails to substantially reorganize the actual keep-set and may therefore not be the main lever for preserving reasoning behavior. We instead frame reasoning KV compression as a behavior-preserving structured consolidation problem. CASK partitions the decode-time reasoning trace into a protected core that anchors answer formation and intermediate state, and mergeable scratch with high redundancy. The core is preserved, while selective consolidation is applied only to the scratch. To address prompt-heavy regimes where the prefix can exhaust the budget before decode-stage compression becomes active, CASK further uses a two-stage design: prefix eviction followed by decode-stage consolidation. On the H100 reasoning gate, CASK shows higher full-KV continuation fidelity than TriAttention at matched budgets on both AIME24 and AIME25, with recurring cask@384 > triattention@512 crossings. In prompt-heavy replay, multi_news and vcsum act as decode-active witnesses, while qmsum and gov_report expose the prefix_budget_exhausted boundary. The overall evidence supports a simple conclusion: effective reasoning KV compression depends less on more elaborate scorer engineering than on combining core preservation with selective scratch consolidation to lower the usable budget frontier.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4. Despite LLMs' prowess in tasks like writing assistance,…
Code GenerationIn-Context LearningLogical ReasoningMachine TranslationSTAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation
Video reasoning segmentation demands pixel-accurate object tracking across hundreds of frames under complex natural language queries, producing dense spatiotemporal tokens whose quadratic self-attention cost makes long-v…
Natural Language QueriesObject TrackingWhen Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces inflate both training and inference cost. Existing CoT compression methods fa…
Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains
Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning metho…
Reinforcement LearningMathematical ReasoningCan Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
Long chain-of-thought (Long-CoT) reasoning improves accuracy in LLMs, yet its verbose, self-reflective style often hinders effective distillation into small language models (SLMs). We revisit Long-CoT compression through…
Large Language ModelMathematical Reasoning