x1: Learning to Think Adaptively Across Languages and Cultures

TL;DR

This paper introduces x1, a reasoning model that adaptively chooses the most advantageous language for each instance, improving multilingual reasoning and cultural understanding in large language models.

Contribution

The work presents a novel approach to adaptive multilingual reasoning that isolates language effects and demonstrates benefits across diverse tasks without expanding model knowledge.

Findings

Adaptive reasoning improves multilingual mathematical problem solving.

Cultural languages enhance culturally grounded task performance.

Scaling reduces but does not eliminate cross-lingual disparities.

Abstract

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.