ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection

• URL: http://arxiv.org/abs/2602.21887v1
• Date: Wed, 25 Feb 2026 13:10:58 GMT
• Title: ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
• Authors: Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li, Shujian Huang,
• Abstract summary: We propose ExpLang, a novel post-training pipeline that enables on-policy thinking language selection to improve exploration and exploitation during reinforcement learning.<n>We show that our method steadily outperforms English-only training with the same training budget, while showing high thinking language compliance for both seen and unseen languages.
• Score: 39.813397419564936
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current large reasoning models (LRMs) have shown strong ability on challenging tasks after reinforcement learning (RL) based post-training. However, previous work mainly focuses on English reasoning in expectation of the strongest performance, despite the demonstrated potential advantage of multilingual thinking, as well as the requirement for native thinking traces by global users. In this paper, we propose ExpLang, a novel LLM post-training pipeline that enables on-policy thinking language selection to improve exploration and exploitation during RL with the use of multiple languages. The results show that our method steadily outperforms English-only training with the same training budget, while showing high thinking language compliance for both seen and unseen languages. Analysis shows that, by enabling on-policy thinking language selection as an action during RL, ExpLang effectively extends the RL exploration space with diversified language preference and improves the RL exploitation outcome with leveraged non-English advantage. The method is orthogonal to most RL algorithms and opens up a new perspective on using multilinguality to improve LRMs.

Related papers

• Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation [73.54930910609328]
  We propose LcRL, a multilingual search-augmented reinforcement learning framework.<n>LcRL integrates a language-coupled Group Relative Policy Optimization into the policy and reward models.<n>We adopt the language-coupled group sampling in the rollout module to reduce knowledge bias, and regularize an auxiliary anti-consistency penalty in the reward models to mitigate the knowledge conflict.
  arXiv  Detail & Related papers  (2026-01-21T11:32:32Z)
• Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering [44.596434537567916]
  We propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE)<n>MRRE consistently enhances non-English reasoning by an average gain of 5.48% and up to 7.54% in low-resource languages (Thai and Swahili)
  arXiv  Detail & Related papers  (2025-11-28T14:40:27Z)
• Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective [52.452449102961225]
  This study proposes a novel cross-linguistic perspective to investigate reasoning generalization.<n>Our findings reveal that cross-lingual transferability varies significantly across initial model, target language, and training paradigm.<n>Our study challenges the assumption that LRM reasoning mirrors human cognition, providing critical insights for the development of more language-agnostic LRMs.
  arXiv  Detail & Related papers  (2025-10-02T17:49:49Z)
• When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners [111.50503126693444]
  We show that language-specific ablation consistently boosts multilingual reasoning performance.<n>Compared to post-training, our training-free ablation achieves comparable or superior results with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-05-21T08:35:05Z)
• Scaling Test-time Compute for Low-resource Languages: Multilingual Reasoning in LLMs [3.9530780161144667]
  We investigate the multilingual mechanism by which Large Language Models internally operate in a latent space biased toward their inherently dominant language.<n>We train models to generate the chain-of-thought (CoT) in English while outputting the final response in the target language, given input in the low-resource language.<n>Our experiments demonstrate that this approach, named English-Pivoted CoT Training, outperforms other baselines, with up to 28.33% improvement.
  arXiv  Detail & Related papers  (2025-04-02T16:58:36Z)
• Demystifying Multilingual Chain-of-Thought in Process Reward Modeling [86.98098988779809]
  We tackle the challenge of extending process reward models (PRMs) to multilingual settings.<n>We train multilingual PRMs on a dataset spanning seven languages, which is translated from English.<n>Our results highlight the sensitivity of multilingual PRMs to both the number of training languages and the volume of English data.
  arXiv  Detail & Related papers  (2025-02-18T09:11:44Z)
• AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought [40.16140566668239]
  We introduce AdaMCOT, a framework that enhances multilingual factual reasoning.<n>AdaMCOT dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses.<n>Our evaluation demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency.
  arXiv  Detail & Related papers  (2025-01-27T15:48:57Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models [79.46179534911019]
  Large language models (LLMs) have demonstrated multilingual capabilities, yet they are mostly English-centric due to imbalanced training corpora.<n>We extend the evaluation to real-world user queries and non-English-centric LLMs, offering a broader examination of multilingual performance.
  arXiv  Detail & Related papers  (2024-03-15T12:47:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.