# Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning

arXiv: https://arxiv.org/abs/2609.10445 · HTML: https://mlsanity.com/paper/2609.10445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 49 of its 92 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 49)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning](https://mlsanity.com/paper/2402.06619/) (2024)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [Llama-Nemotron: Efficient Reasoning Models](https://mlsanity.com/paper/2505.00949/) (2025)
- [Olmo 3](https://mlsanity.com/paper/2512.13961/) (2025)
- [NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://mlsanity.com/paper/2508.14444/) (2025)
- [Magistral](https://mlsanity.com/paper/2506.10910/) (2025)
- [Crosslingual Reasoning through Test-Time Scaling](https://mlsanity.com/paper/2505.05408/) (2025)
- [Question Translation Training for Better Multilingual Reasoning](https://mlsanity.com/paper/2401.07817/) (2024)
- [mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models](https://mlsanity.com/paper/2406.02301/) (2024)
- [AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale](https://mlsanity.com/paper/2505.08311/) (2025)
- [Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning](https://mlsanity.com/paper/2507.05418/) (2025)
- [LangBridge: Multilingual Reasoning Without Multilingual Supervision](https://mlsanity.com/paper/2401.10695/) (2024)
- [Language-Specific Latent Process Hinders Cross-Lingual Performance](https://mlsanity.com/paper/2505.13141/) (2025)
- [Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?](https://mlsanity.com/paper/2505.17407/) (2025)
- [Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2510.07300/) (2025)
- [MMATH: A Multilingual Benchmark for Mathematical Reasoning](https://mlsanity.com/paper/2505.19126/) (2025)
- [Tiny Aya: Bridging Scale and Multilingual Depth](https://mlsanity.com/paper/2603.11510/) (2026)
- [Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models](https://mlsanity.com/paper/2506.05850/) (2025)
- [LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy](https://mlsanity.com/paper/2502.11405/) (2025)
- [The Multilingual Divide and Its Impact on Global AI Safety](https://mlsanity.com/paper/2505.21344/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures](https://mlsanity.com/paper/2510.24081/) (2025)

## Abstract (arXiv)

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.