VaSE improves KV cache eviction accuracy for reasoning models by over 4% versus prior eviction methods at 4x compression through value-magnitude protection and stochastic diversity.
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. However, these extended generations incur substantial memory footprint and computational overhead, bottlenecking LRMs' efficiency. This work uses attention maps to analyze the influence of reasoning traces and uncover an interesting phenomenon: only some decision-critical tokens in a reasoning trace steer the model toward the final answer, while the remaining tokens contribute negligibly. Building on this observation, we propose Dynamic Thinking-Token Selection (DynTS). This method identifies decision-critical tokens and retains only their associated Key-Value (KV) cache states during inference, evicting the remaining redundant entries to optimize efficiency.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
VaSE improves KV cache eviction accuracy for reasoning models by over 4% versus prior eviction methods at 4x compression through value-magnitude protection and stochastic diversity.