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

2026-02-25 · Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li, Shujian Huang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.21887

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Exploration and Exploitation Errors Are Measurable for Language Model Agents

2026-04-14 · Jaden Park, Jungtaek Kim, Jongwon Jeong, Robert D. Nowak 외 arxiv

Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and explo…

Representation-Driven Reinforcement Learning

2023-05-31 · Ofir Nabati, Guy Tennenholtz, Shie Mannor

We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitatio…

Multi-Armed Bandits reinforcement-learning Reinforcement Learning

DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off

2026-04-15 · Xiaofan Li, Ming Yang, Zhiyuan Ma, Shichao Ma 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs). However, effectively managing the exploration and exploitation trade…

Reinforcement Learning Mathematical Reasoning

ReLaX: Reasoning with Latent Exploration for Large Reasoning Models

2025-12-08 · Shimin Zhang, Xianwei Chen, Yufan Shen, Ziyuan Ye 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated remarkable potential in enhancing the reasoning capability of Large Reasoning Models (LRMs). However, RLVR often drives the policy toward ov…