@inproceedings{zhang-etal-2026-think,
    title = "Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning",
    author = "Zhang, Xue  and
      Liang, Yunlong  and
      Meng, Fandong  and
      Zhang, Songming  and
      Huang, Kaiyu  and
      Chen, Yufeng  and
      Jinan, Xu  and
      Zhou, Jie",
    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.951/",
    pages = "20766--20783",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the ``think-then-answer'' paradigm, which enhances both accuracy and interpretability. However, current LRMs exhibit two critical limitations when processing non-English languages: (1) They often struggle to maintain input-output language consistency; (2) They generally perform poorly with wrong reasoning paths and lower answer accuracy compared to English. These limitations significantly compromise the interpretability of reasoning processes and degrade the user experience for non-English speakers, hindering the global deployment of LRMs. To address these limitations, we propose M-Thinker, which is trained by the GRPO algorithm that involves a Language Consistency (LC) reward and a novel Cross-lingual Thinking Alignment (CTA) reward. Specifically, the LC reward defines a strict constraint on the language consistency between the input, thought, and answer. Besides, the CTA reward compares the model{'}s non-English reasoning paths with its English reasoning path to transfer its own reasoning capability from English to non-English languages. Through an iterative RL procedure, our M-Thinker-1.5B/4B/7B models not only achieve nearly 100{\%} language consistency and superior performance on two multilingual benchmarks (MMATH and PolyMath), but also exhibit excellent generalization on out-of-domain languages."
}