Long-output reasoning shifts the KV-cache bottleneck from the fixed prompt to the generated trace. Existing reasoning-cache eviction methods largely treat cached entries as routing objects, estimating whether an old key will still be read, will recur, or can be replaced. This routing-only view overlooks two effects: lo...
Han Yu, Wen-Hui Zhu, Xi-Wen Chen et al.· 0 citations
LatentPress is introduced, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference.
TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion, achieves high success rates early in training while unaided GRPO requires substantially more optimization steps to reach comparable levels.