Reinforced Efficient Reasoning via Semantically Diverse Exploration

arXiv (Cornell University)

Abstract

Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensions improve upon vanilla RLVR (e.g., GRPO) by providing tree-based reasoning rollouts that enable fine-grained and segment-level credit assignment. However, existing methods still suffer from limited exploration diversity and inefficient reasoning. To address the above challenges, we propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs. To encourage more diverse reasoning exploration, our method incorporates a semantic-entropy-based branching strategy and an $\varepsilon$-exploration mechanism. The former operates on already sampled reasoning rollouts to capture semantic uncertainty and select branching points with high semantic divergence to generate new successive reasoning paths, whereas the latter stochastically initiates reasoning rollouts from the root, preventing the search process from becoming overly local. To improve efficiency, we design a length-aware segment-level advantage estimator that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains. Extensive experiments on various mathematical reasoning benchmarks with Qwen and Llama models validate the effectiveness and efficiency of ROSE. Codes are available at https://github.com/ZiqiZhao1/ROSE-rl.

Authors 12

1. Ziqi Zhao

   Shandong University

   Affiliation as printed

   Shandong University

2. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University

3. Jiahong Zou

   Shandong University

   Affiliation as printed

   Shandong University

4. Liu Yang

   Shandong University

   Affiliation as printed

   Shandong University

5. Zhiwei Xu

   Shandong University

   Affiliation as printed

   Shandong University

6. Xuri Ge

   Shandong University

   Affiliation as printed

   Shandong University

7. Zhumin Chen

   Shandong University

   Affiliation as printed

   Shandong University

8. Xinyu Ma

   Baidu (China)

   Affiliation as printed

   Baidu Inc

9. Daiting Shi

   Baidu (China)

   Affiliation as printed

   Baidu Inc

10. Shuaiqiang Wang

    Baidu (China)

    Affiliation as printed

    Baidu Inc

11. Dawei Yin

    Baidu (China)

    Affiliation as printed

    Baidu Inc

12. Xin Xin

    Shandong University

    Affiliation as printed

    Shandong University