Language models learn to evict KV cache entries end-to-end via reinforcement learning from outcome reward alone, achieving 2-3x cache compression while maintaining accuracy on Countdown, AMC, and AIME tasks.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
A large model generates a compact reasoning signal that a small model uses to solve tasks, reducing the large model's output tokens by up to 60% on benchmarks like AIME and GPQA.
MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.
citing papers explorer
-
Neural Garbage Collection: Learning to Forget while Learning to Reason
Language models learn to evict KV cache entries end-to-end via reinforcement learning from outcome reward alone, achieving 2-3x cache compression while maintaining accuracy on Countdown, AMC, and AIME tasks.
-
When Less is Enough: Efficient Inference via Collaborative Reasoning
A large model generates a compact reasoning signal that a small model uses to solve tasks, reducing the large model's output tokens by up to 60% on benchmarks like AIME and GPQA.
-
MEMENTO: Teaching LLMs to Manage Their Own Context
MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.