{"ID":5551970,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T06:09:39.680448252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00485","arxiv_id":"2607.00485","title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","abstract":"Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reason in other languages. A natural solution is to transfer the model's English reasoning ability to target languages. However, existing transfer approaches typically rely on distilled target-language reasoning traces from stronger LRMs or online supervision from external judge models, which are costly and difficult to scale. In this paper, we propose PCS (Progressive Code-Switching), a more efficient transfer framework that requires only lightweight translation without any stronger model for distillation or judging. PCS first constructs code-switched reasoning traces by translating a subset of English reasoning steps into the target language, and uses them to initialize the model's code-switching ability via supervised fine-tuning. It then applies reinforcement learning with a step-level language consistency curriculum, progressively raising the target-language ratio until the model reasons entirely in the target language. This progressive design provides a smooth transfer path that avoids the instability and performance degradation commonly observed when directly enforcing target-language reasoning. Experiments on multiple benchmarks and five typologically diverse languages show that PCS substantially narrows the performance gap between target-language and English reasoning, yielding more language-consistent reasoning while maintaining competitive accuracy.","short_abstract":"Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reason in other languages. A natural solution is to transfer the model's English reasoning ability to target languages. However, existing transfer approaches typically rely...","url_abs":"https://arxiv.org/abs/2607.00485","url_pdf":"https://arxiv.org/pdf/2607.00485v1","authors":"[\"Zhijun Wang\",\"Junxiao Liu\",\"Hao Zhou\",\"Hao-Ran Wei\",\"Baosong Yang\",\"Shujian Huang\"]","published":"2026-07-01T06:13:16Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}