RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior

Junyao Yang, Jianwei Wang, Huiping Zhuang, Cen Chen, Ziqian Zeng†

† Corresponding author

Treating reasoning capability as a prior identifies and preserves reasoning-sensitive parameters during model merging. This enhances domain-specific performance while retaining long chain-of-thought abilities.

Paper arXiv Code