构建14语言的可验证推理环境，支持大规模跨语言训练
Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environments
- 通过程序化生成技术在14种语言中构造可验证推理题
- 翻译94个任务模板并经母语者验证，确保语言自然性
- 适合研究多语言推理模型与强化学习中的跨语言泛化
我们提出Multilingual Reasoning Gym，是Reasoning Gym（Stojanovski等，2025）的多语言扩展，可在14种语言中程序化生成可验证的推理问题。通过在10种语言中对94个任务的模板进行翻译，并结合母语者验证及代码或模板的针对性调整，确保语言自然性。该框架保留了原始Reasoning Gym的核心优势：近乎无限的问题实例生成能力与可调难度，且仍适用于基于可验证奖励的强化学习与评估场景。由于环境的程序化特性，不同语言间的问题保持平行，实现大规模跨语言并行数据生成。我们已开源实现，以支持多语言推理模型的研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。