Reasoning models are supposed to be better at hard tasks because they “think” before answering. In practice, that extra step-by-step process creates a new attack surface: if you can push the model into overthinking, you can make it spend far more tokens than normal and slow it down for everyone else. That’s the core finding from a recent study presented at ICML 2026 by researchers from Zhejiang University and Alibaba. They show that carefully co…
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.