{"slug": "grpo-beyond-english-a-large-scale-study-of-grpo-in-non-english-and-multilingual", "title": "GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings", "summary": "A large-scale empirical study from arXiv (2608.13698v1) finds that training language models to reason in their native language via Group Relative Policy Optimization (GRPO) leaves only a small gap to English reasoning, with strong crosslingual transfer but also language-specific regressions. The study, covering multiple base models and training languages, concludes that RLVR beyond English can yield broad gains but requires broad evaluation to detect regressions.", "body_md": "arXiv:2608.13698v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/grpo-beyond-english-a-large-scale-study-of-grpo-in-non-english-and-multilingual", "canonical_source": "https://arxiv.org/abs/2608.13698", "published_at": "2026-08-17 04:00:00+00:00", "updated_at": "2026-08-17 04:14:04.650474+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models"], "entities": ["arXiv", "GRPO", "RLVR"], "alternates": {"html": "https://wpnews.pro/news/grpo-beyond-english-a-large-scale-study-of-grpo-in-non-english-and-multilingual", "markdown": "https://wpnews.pro/news/grpo-beyond-english-a-large-scale-study-of-grpo-in-non-english-and-multilingual.md", "text": "https://wpnews.pro/news/grpo-beyond-english-a-large-scale-study-of-grpo-in-non-english-and-multilingual.txt", "jsonld": "https://wpnews.pro/news/grpo-beyond-english-a-large-scale-study-of-grpo-in-non-english-and-multilingual.jsonld"}}