AI 终于能不用英语思考了
现在的推理模型有个怪癖：你用中文问它，它脑子里其实在用英语想，最后再翻译回中文。这篇论文直接把这个毛病治了——他们训练了一个 33 亿参数的小模型，让它在 60 种语言里都能用提问者的语言直接推理，成功率超过 93%。做法不玄乎：把多语言数据混进训练集，再配一个足够强的英语推理底座，模型就学会了「用你的语言思考」这件事，而且能推广到没见过的语言。它不是你明天能用上的产品，但它指向一个趋势：AI 的多语言能力不该靠翻译，而该靠真正的母语思维。
📄 原文摘要(英文)
Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in English regardless of the language they are prompted in. This is inaccessible for non-English-speaking users, risks losing the intent of the original question, and forgoes knowledge more readily expressed in the target language. In this work, we advance L2 reasoning, the ability of a model to reason consistently in the language of the user's prompt, thus building an in-language bridge between the prompt and the answer. We approach this problem from a data-centric angle, investigating how to optimize data composition and scheduling in SFT for reasoning generalization. Building Tiny Aya L2-Thinker at 3.35B scale, we achieve an L2 reasoning rate above 93% across 60 languages on 6 benchmarks spanning math, commonsense reasoning, instruction following, open-ended generation, and cultural reasoning while keeping performance strong. We show the path to generalizing L2 reasoning to held-out languages goes through broader language coverage, readily available multilingual non-reasoning data, and a sufficient English reasoning backbone. These findings indicate that reasoning is a language-agnostic behavior that can be transferred across typologically diverse languages through careful data mixing and without requiring reasoning supervision in every target language. We release our model weights and multilingual reasoning data to support further research on accessible, in-language reasoning.