Author

J. Sakuma

View on Semantic Scholar

1 paper indexed here

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.

Preprint Aug 2026

Capability-Routed Guard: Defending Large Reasoning Models Against Reasoning-Centric Jailbreaks

Capability-Routed Guard is introduced, a model-agnostic inference-time guardrail for closed-source LRMs, where defenders cannot inspect hidden reasoning traces or modify model weights, and its components contribute complementary benefits, highlighting the importance of coordinated defense mechanisms for securing large reasoning models.

Yiyong Liu, Yixin Wu, J. Sakuma · 0 citations