一作ACL 2026Poster· Natural Language Processing
R eason A ny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
Junyao Yang · Chen Qian · Wen Shen · Yong Liu · Jing Shao · Dongrui Liu
摘要
Large Reasoning Models (LRMs) with long chain-of-thought reasoning have recently achieved remarkable success. Yet, equipping domain-specialized models with such reasoning capabilities, referred to as “Reasoning + X”, remains a significant challenge. While model merging offers a promising training...