Self-Improving Multilingual Long Reasoning via Translation-Reasoning Integrated Training

LiuJunxiao, Zhijun Wang, Yixiao Li, Jackie Lai, Liqian Huang, Xin Huang, Xue Han, Junlan Feng, Shujian Huang

Self-Improving Multilingual Long Reasoning via Translation-Reasoning Integrated Training: 18 upvotes on Hugging Face Daily Papers, #11 of 43 papers on 2026-02-09. Day-by-day upvote history.

Long reasoning models often struggle in multilingual settings: they tend to reason in English for non-English questions; when constrained to reasoning in the question language, accuracies drop substantially. The struggle is caused by the limited abilities for both multilingual question understanding and multilingual reasoning. To address both problems, we propose TRIT (Translation-Reasoning Integrated Training), a self-improving framework that integrates the training of translation into multilingual reasoning. Without external feedback or additional multilingual data, our method jointly enhances multilingual question understanding and response generation. On MMATH, our method outperforms multiple baselines by an average of 7 percentage points, improving both answer correctness and language consistency. Further analysis reveals that integrating translation training improves cross-lingual question alignment by over 10 percentage points and enhances translation quality for both mathematical questions and general-domain text, with gains up to 8.4 COMET points on FLORES-200.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.