Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced models utilize deliberate "thinking" steps to systematically enhance answer quality. In this paper, we propose leveraging these high-quality outputs generated by reasoning-intensive models to improve less computationally demanding, non-reasoning models. We explore and compare methodologies for utilizing the answers produced by reasoning models to train and improve non-reasoning models. Through straightforward Supervised Fine-Tuning (SFT) experiments on established benchmarks, we demonstrate consistent improvements across various benchmarks, underscoring the potential of this approach for advancing the ability of models to answer questions directly.
@article{arxiv.2504.09639,
title = {Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability},
author = {Haotian Wang and Han Zhao and Shuaiting Chen and Xiaoyu Tian and Sitong Zhao and Yunjie Ji and Yiping Peng and Xiangang Li},
journal= {arXiv preprint arXiv:2504.09639},
year = {2025}
}