We have 3 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is shown that reasoning concentrates a model's errors: the probability that two independently drawn wrong answers coincide rises in all ten dataset-scale comparisons, and in nine of nine after restricting both arms to the problems each gets wrong.
It is argued that a cheap deterministic check, run before an action takes effect, is an effective and underused form of agent oversight, and it is studied across two action modalities in one framework.
This work proposes DistillCache, a reinforcement learning framework that formulates KV-cache eviction as a sequential decision problem and demonstrates the effectiveness of learned, distribution-aware policies for memory-efficient long-context LLM inference.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
