ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
Junyao Yang, Chen Qian‡, Dongrui Liu†, Wen Shen, Yong Liu†, Jing Shao†
† Corresponding authors · ‡ Project lead; work conducted during an internship at Shanghai AI Lab
Contrastive Gradient Identification separates reasoning-related parameters from task-specific knowledge to prevent destructive collapse during model merging. The method transfers robust chain-of-thought capabilities into domain-specific models without additional training.