@inproceedings{an-etal-2025-long,
    title = "Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition",
    author = "An, Chenxin  and
      Xie, Zhihui  and
      Li, Xiaonan  and
      Zhong, Ming  and
      Gong, Shansan  and
      Li, Lei  and
      Zhang, Jun  and
      Xu, Jingjing  and
      Kong, Lingpeng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1751/",
    pages = "34506--34522",
    ISBN = "979-8-89176-332-6",
    abstract = "Reasoning models have demonstrated remarkable performance on complex tasks by generating long reasoning traces prior to producing final answers. However, previous research on long-context scaling in language models has generally focused on managing lengthy input prompts instead of producing long outputs. To leverage the strong long context understanding abilities of current models, we introduce Understanding-to-Reasoning Transition (URT) fine-tuning, a sequence-level curriculum learning framework that gradually shifts a model{'}s focus from interpreting long chain-of-thoughts to generating them. By incorporating partial reasoning steps in the input context, URT naturally exposes the model to diverse prompt lengths during training, preserving its performance on long-context comprehension while developing advanced reasoning capabilities. Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, reveal that our approach surpasses standard fine-tuning by over 10{\%}, while maintaining robust performance on the understanding tasks in RULER."
}