多语言推理健身房：多语言的程序化推理环境扩展
Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environments
AI总结：
Multilingual Reasoning Gym通过多语言程序化生成可验证推理问题，支持跨语言大规模数据生成和强化学习研究。
摘要：
我们提出了Multilingual Reasoning Gym，这是Reasoning Gym（Stojanovski等，2025）的扩展，能够跨14种语言程序化生成可验证的推理问题。我们对94个任务的模板进行了10种语言的母语者验证，并针对目标代码或模板进行调整以确保语言自然性。Multilingual Reasoning Gym保留了原始Reasoning Gym中程序化生成方法的核心优势，如几乎无限的问题实例生成能力和可调节的难度，并且可以直接用于可验证奖励的强化学习和评估设置。Multilingual Reasoning Gym中的问题在不同语言间是平行的，由于环境的程序化性质，这使得能够大规模生成跨语言的平行数据。我们发布我们的实现以支持多语言推理模型的研究。
英文摘要：
We present the Multilingual Reasoning Gym, an extension of Reasoning Gym (Stojanovski et al., 2025), that procedurally generates verifiable reasoning problems across 14 languages. We translate templates for 94 tasks with native-speaker validation in 10 languages and targeted code or template adaptations to ensure linguistic naturalness. The Multilingual Reasoning Gym preserves the core benefits of the procedural generation approach used in the original Reasoning Gym, such as virtually unlimited problem instance generation and adjustable difficulty, and remains directly usable for Reinforcement Learning from Verifiable Rewards and evaluation settings. Problems in the Multilingual Reasoning Gym are parallel across languages, enabling crosslingually parallel data generation at massive scale due to the procedural nature of the environments. We release our implementation to support research into multilingual reasoning models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
