Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers

ArXi:2601.07036v2 Announce Type: replace-cross Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is largely driven by a small set of trigger tokens rather than the instructions themselves. Through attention analysis and controlled prompting experiments, we show that a leading ``Okay'' token induces reasoning behavior, while the newline pattern following ``'' suppresses it. Based on this observation, we propose Mid-Think, a simple.