摘要：具有可验证奖励的强化学习（Reinforcement Learning with Verifiable Rewards，RLVR）通常通过组相对策略优化（Group Relative Policy Optimization，GRPO）进行优化，已成为提升预训练语言模型推理能力的核心方法之一，但现有研究仍然高度以英语为中心。我们针对多语言和非英语 GRPO 开展了一项大规模实证研究，覆盖广泛的基础模型、训练语言以及不同的推理语言奖励设置。我们发现，训练模型以母语进行推理，通常与训练其使用英语推理相比仅存在较小差距。我们还观察到显著的跨语言迁移：在一种语言上训练，往往能够提升多种其他语言的性能。然而，具体趋势高度依赖于模型和语言。在某些情况下，以特定语言训练会导致模型在其他语言中的域外能力出现严重退化。我们的分析表明，英语以外的 RLVR 可以带来广泛的跨语言收益，但也需要进行广泛评估，以发现特定语言上的能力退化。

Abstract:Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capabilities of pretrained language models but current studies remain heavily English-centric. We conduct a large-scale empirical study of multilingual and non-English GRPO across a wide range of base models, training languages, and different reasoning language rewards. We find that training to reason in the native language often leaves only a small gap to training for English reasoning. We further observe strong crosslingual transfer: training in one language often improves performance in many others. However, specific trends are highly model- and language-dependent. In some cases, training in a particular language induces severe regressions on out-of-domain capabilities in other languages. Our analysis shows that RLVR beyond English can provide broad crosslingual gains, but also requires broad evaluation to detect language-specific regressions.