English
Related papers

Related papers: Learning to Hint for Reinforcement Learning

200 papers

Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent reasoning benefit…

Computation and Language · Computer Science 2025-10-24 Zhenrui Yue , Bowen Jin , Huimin Zeng , Honglei Zhuang , Zhen Qin , Jinsung Yoon , Lanyu Shang , Jiawei Han , Dong Wang

Reinforcement learning (RL) with group relative policy optimization (GRPO) has become a widely adopted approach for enhancing the reasoning capabilities of multimodal large language models (MLLMs). While GRPO enables long-chain reasoning…

Artificial Intelligence · Computer Science 2026-03-03 Haowen Gao , Zhenyu Zhang , Liang Pang , Fangda Guo , Hongjian Dou , Guannan Lv , Shaoguo Liu , Tingting Gao , Huawei Shen , Xueqi Cheng

Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout budget is small,…

Machine Learning · Computer Science 2026-02-02 Youngeun Kim

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Policy Optimization (GRPO) was proposed to use the within-group sample mean as a baseline for…

Machine Learning · Computer Science 2026-04-23 Hu Wang , Congbo Ma , Ian Reid , Mohammad Yaqub

Reinforcement learning with verifiable rewards (RLVR) can improve low-$k$ reasoning accuracy while narrowing solution coverage on challenging math questions, and pass@1 gains do not necessarily translate into better large-$k$ performance.…

Artificial Intelligence · Computer Science 2026-04-10 Pei-Xi Xie , Che-Yu Lin , Cheng-Lin Yang

Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to…

Machine Learning · Computer Science 2025-10-14 Yang Chen , Menglin Zou , Jiaqi Zhang , Yitan Zhang , Junyi Yang , Gael Gendron , Libo Zhang , Jiamou Liu , Michael J. Witbrock

Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level…

Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithms like GRPO often suffer from exploration collapse, where the models prematurely converge…

Artificial Intelligence · Computer Science 2026-05-19 Haoxuan Chen , Tianming Liang , Wei-Shi Zheng , Jian-Fang Hu

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to…

Machine Learning · Computer Science 2025-09-09 Ziheng Li , Zexu Sun , Jinman Zhao , Erxue Min , Yongcheng Zeng , Hui Wu , Hengyi Cai , Shuaiqiang Wang , Dawei Yin , Xu Chen , Zhi-Hong Deng

We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Group Relative Policy Optimization (GRPO). In contrast to Reinforcement Learning with…

Machine Learning · Computer Science 2026-05-21 Xingwei Gan , Ying Zhu

Reinforcement learning has become the primary paradigm for aligning large language models (LLMs) on complex reasoning tasks, with group relative policy optimization (GRPO) widely used in large-scale post-training. However, GRPO faces…

Machine Learning · Computer Science 2026-01-08 Amir Hossein Yari , Fajri Koto

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Cryptography and Security · Computer Science 2025-07-08 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its…

Machine Learning · Computer Science 2025-10-21 Kangqi Ni , Zhen Tan , Zijie Liu , Pingzhi Li , Tianlong Chen

Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinforcement Learning (RL) paradigms like Group Relative Policy…

Machine Learning · Computer Science 2026-01-28 Kishan Panaganti , Zhenwen Liang , Wenhao Yu , Haitao Mi , Dong Yu

Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging…

Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle…

Machine Learning · Computer Science 2021-05-18 Hanbo Zhang , Site Bai , Xuguang Lan , David Hsu , Nanning Zheng

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

Machine Learning · Computer Science 2025-08-11 Si Shen , Peijun Shen , Wenhua Zhao , Danhao Zhu

An appropriate reward function is of paramount importance in specifying a task in reinforcement learning (RL). Yet, it is known to be extremely challenging in practice to design a correct reward function for even simple tasks.…

Machine Learning · Computer Science 2023-04-19 Dingwen Kong , Lin F. Yang