MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller
MetaCtrl is introduced, a lightweight controller that adaptively regulates a frozen reasoner without predefined token budgets or reasoner retraining, and is established as a plug-and-play controller for improving reasoning accuracy while substantially reducing inference-time generation.
Zhi-Bin Wen, Tao Han, Lei Bai et al.
· 1 citation