# x1: Learning to Think Adaptively Across Languages and Cultures

arXiv: https://arxiv.org/abs/2604.16917 · HTML: https://mlsanity.com/paper/2604.16917/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [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)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies](https://mlsanity.com/paper/2404.15238/) (2024)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://mlsanity.com/paper/2310.14799/) (2023)
- [Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations](https://mlsanity.com/paper/2310.20246/) (2023)
- [Large Language Models as Superpositions of Cultural Perspectives](https://mlsanity.com/paper/2307.07870/) (2023)
- [Crosslingual Reasoning through Test-Time Scaling](https://mlsanity.com/paper/2505.05408/) (2025)
- [Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap](https://mlsanity.com/paper/2501.02448/) (2025)
- [Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning](https://mlsanity.com/paper/2502.17407/) (2025)
- [SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment](https://mlsanity.com/paper/2501.03681/) (2025)
- [The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights](https://mlsanity.com/paper/2405.01345/) (2024)
- [Demystifying Multilingual Chain-of-Thought in Process Reward Modeling](https://mlsanity.com/paper/2502.12663/) (2025)
- [Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models](https://mlsanity.com/paper/2411.01141/) (2024)
- [Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challenges](https://mlsanity.com/paper/2412.12686/) (2024)
- [LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning](https://mlsanity.com/paper/2511.10229/) (2025)

## Built on by (most cited first, 2 of 2)

- [CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs](https://mlsanity.com/paper/2606.01879/) (2026)
- [CRISP: Cultural Reward Modeling for Implicit Situated Propriety](https://mlsanity.com/paper/2609.34345/) (2026)

## Abstract (arXiv)

Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single dominant language. In this work, we introduce x1, a family of reasoning models that can adaptively reason in an advantageous language on a per-instance basis. To isolate the effect of reasoning-language choice, x1 is constructed without expanding the model's knowledge boundaries and is trained by contrasting linguistically distinct reasoning trajectories for the same input. Our extensive experiments demonstrate the benefits of adaptive multilingual reasoning across multilingual mathematical reasoning and culturally grounded tasks. Moreover, our results challenge a simplistic view of scaling laws: while scaling reduces cross-lingual disparities in procedural domains such as math reasoning, it does not eliminate the advantages of culture-associated languages in culturally grounded tasks, as we empirically show that such reasoning enables more efficient and accurate cultural knowledge recall. Overall, our findings establish language choice as a functional component of reasoning, with implications for building more generalist and globally competent reasoning models.