@inproceedings{li-etal-2026-reasoning,
    title = "Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression",
    author = "Li, Chengzhengxu  and
      Liu, Xiaoming  and
      Zhang, Zhaohan  and
      Liu, Shengchao  and
      Ma, Guoxin  and
      Lan, Yu  and
      Wang, Cong  and
      Shen, Chao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1810/",
    pages = "39014--39034",
    ISBN = "979-8-89176-390-6",
    abstract = "Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing works focus on compressing generated CoT in reasoning, which impairs the necessary information for deriving the correct answer. In this work, we propose post-reasoning, a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for LLMs. We find that post-reasoning significantly reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and the reliability of the contextual CoT generation.Therefore, we propose Upfront CoT (UCoT), an efficient post-reasoning framework for CoT compression. UCoT trains a lightweight model (compressor) to provide contextual CoT in form of soft tokens and trains the LLM (executor) to leverage this contextual CoT for producing the final answer. Extensive experiments show that UCoT maintains the powerful reasoning ability of executor while significantly reducing the length of CoT. It is worth mentioning that when applying UCoT to the Qwen2.5-7B-Instruct model, the usage of tokens on GSM8K dataset is reduced by 50{\%}, while the performance is 3.08{\%} higher than that of the state-of-the-art (SOTA) method. The code is available at: https://github.com/czx-li/UCoT."
}