# Learning When to Translate for Multilingual Reasoning

arXiv: https://arxiv.org/abs/2606.02465 · HTML: https://mlsanity.com/paper/2606.02465/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use](https://mlsanity.com/paper/2509.01055/) (2025)
- [xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning](https://mlsanity.com/paper/2401.07037/) (2024)
- [Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap](https://mlsanity.com/paper/2501.02448/) (2025)
- [Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning](https://mlsanity.com/paper/2507.05418/) (2025)
- [Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?](https://mlsanity.com/paper/2505.17407/) (2025)
- [Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?](https://mlsanity.com/paper/2510.27269/) (2025)
- [Crosslingual On-Policy Self-Distillation for Multilingual Reasoning](https://mlsanity.com/paper/2605.09548/) (2026)
- [Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe](https://mlsanity.com/paper/2502.09056/) (2025)
- [TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning](https://mlsanity.com/paper/2603.25419/) (2026)
- [RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior](https://mlsanity.com/paper/2508.03140/) (2025)
- [R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning](https://mlsanity.com/paper/2602.05940/) (2026)
- [What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features](https://mlsanity.com/paper/2604.04720/) (2026)

## Built on by (most cited first, 1 of 1)

- [Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning](https://mlsanity.com/paper/2606.06835/) (2026)

## Abstract (arXiv)

Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps, largely due to language-understanding failures when interpreting non-English inputs. Translation into English can mitigate these failures by expressing non-English inputs in a form that RLMs can more reliably interpret, yet translating every input incurs unnecessary inference cost when the model can reason reliably from the original query. To address this challenge, we propose Luar, a Language Understanding Boundary-aware Reinforcement Learning framework that trains RLMs to selectively invoke translation when their direct understanding is unreliable. Luar trains the model to either solve the original input directly or reason over its English translation, encouraging translation only when translator-augmented reasoning is expected to substantially outperform direct reasoning. Across multilingual reasoning benchmarks, Luar outperforms training-based baselines, with particularly large gains on low-resource languages. On Qwen3-4B, it improves average accuracy by 8.4 percentage points over standard GRPO. Further analysis shows that Luar concentrates translator calls on queries where translation benefits reasoning, helping to reduce inference cost. The project will be made publicly available at https://github.com/deokhk/LUAR.