English
Related papers

Related papers: Hierarchical Budget Policy Optimization for Adapti…

200 papers

Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency methods reduce cost by compressing reasoning traces or conditioning budget on perceived…

Artificial Intelligence · Computer Science 2026-05-13 Zhaomeng Zhou , Lan Zhang , Junyang Wang , Mu Yuan , Junda Lin

Reinforcement learning algorithms such as group-relative policy optimization (GRPO) have shown strong potential for improving the mathematical reasoning capabilities of large language models. While a growing body of work seeks to improve…

Machine Learning · Computer Science 2026-05-12 Wenquan Lu , Hai Huang , Enqi Liu , Randall Balestriero

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…

Artificial Intelligence · Computer Science 2025-05-22 Haotian Luo , Haiying He , Yibo Wang , Jinluan Yang , Rui Liu , Naiqiang Tan , Xiaochun Cao , Dacheng Tao , Li Shen

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, recent studies question whether RL genuinely expands reasoning…

Machine Learning · Computer Science 2026-02-04 Dayu Wang , Jiaye Yang , Weikang Li , Jiahui Liang , Yang Li

Exploration is essential in modern learning, from reinforcement learning environments with small neural policies to large language models (LLMs). Existing work, such as DPO, leverages full sequence log-likelihoods to capture an entire…

Machine Learning · Computer Science 2025-08-27 Gaurish Trivedi , Alakh Sharma , Kartikey Singh Bhandari , Dhruv Kumar , Pratik Narang , Jagat Sesh Challa

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Machine Learning · Computer Science 2026-01-26 Jingchu Wang , Bingbing Xu , Yige Yuan , Bin Xie , Xiaoqian Sun , Huawei Shen

Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-answer correctness as feedback signals and rarely capture the…

Artificial Intelligence · Computer Science 2026-04-13 Jinghan Zhang , Fengran Mo , Tharindu Cyril Weerasooriya , Ruimin Dai , Xiaoyan Han , Yanjie Fu , Dakuo Wang , Kunpeng Liu

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Artificial Intelligence · Computer Science 2025-10-02 Yunhao Wang , Ziting Li , Shuai Chen , Tao Liu , Chao Song , Junjie Jiang , Jian Zhu , Peng Gao , Bin Qin

We consider a Continual Reinforcement Learning setup, where a learning agent must continuously adapt to new tasks while retaining previously acquired skill sets, with a focus on the challenge of avoiding forgetting past gathered knowledge…

Machine Learning · Computer Science 2026-02-06 Anthony Kobanda , Rémy Portelas , Odalric-Ambrym Maillard , Ludovic Denoyer

Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible…

Artificial Intelligence · Computer Science 2025-12-09 Jindi Lv , Yuhao Zhou , Zheng Zhu , Xiaofeng Wang , Guan Huang , Jiancheng Lv

Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of rollouts stabilizes training, existing approaches suffer from limited exploration on challenging…

Machine Learning · Computer Science 2026-05-26 Udbhav Bamba , Minghao Fang , Yifan Yu , Haizhong Zheng , Fan Lai

Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typically treat it as a discrete filter or post-hoc regulator rather…

Computation and Language · Computer Science 2026-04-30 Zheng Liu , Mengjie Liu , Siwei Wen , Mengzhang Cai , Bin Cui , Conghui He , Wentao Zhang

Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (LLMs). However, a fundamental tension arises: inference-time methods benefit from diverse…

Machine Learning · Computer Science 2026-05-12 Changhao Li , Yuchen Zhuang , Chenxiao Gao , Haotian Sun , Rushi Qiang , Chao Zhang , Bo Dai

Reinforcement learning with verifiable rewards (RLVR) has recently enhanced the reasoning capabilities of large language models (LLMs), particularly for mathematical problem solving. However, a fundamental limitation remains: as the…

Machine Learning · Computer Science 2025-11-03 Wenhao Deng , Long Wei , Chenglei Yu , Tailin Wu

Budget planning and maintenance optimization are crucial for infrastructure asset management, ensuring cost-effectiveness and sustainability. However, the complexity arising from combinatorial action spaces, diverse asset deterioration,…

Artificial Intelligence · Computer Science 2025-07-28 Amir Fard , Arnold X. -X. Yuan

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing…

Machine Learning · Computer Science 2026-05-14 Jiaming Li , Chenyu Zhu , Nanxi Yi , Youjun Bao , Li Sun , Quanying Lv , Xiang Fang , Daizong Liu , Jianjun Li , Kun He , Bowen Zhou , Zhiyuan Ma

Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only…

Machine Learning · Computer Science 2024-06-27 Yu Luo , Fuchun Sun , Tianying Ji , Xianyuan Zhan

Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or…

Machine Learning · Computer Science 2024-01-09 Wentse Chen , Shiyu Huang , Yuan Chiang , Tim Pearce , Wei-Wei Tu , Ting Chen , Jun Zhu