English
Related papers

Related papers: Token Hidden Reward: Steering Exploration-Exploita…

200 papers

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all…

Machine Learning · Computer Science 2026-04-06 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this…

Machine Learning · Computer Science 2025-10-14 Jens Tuyls , Dylan J. Foster , Akshay Krishnamurthy , Jordan T. Ash

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks.…

Computation and Language · Computer Science 2025-05-30 Hongzhan Chen , Tao Yang , Shiping Gao , Ruijun Chen , Xiaojun Quan , Hongtao Tian , Ting Yao

Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with…

Machine Learning · Computer Science 2026-05-29 Jonathan Williams , Esin Tureci

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Artificial Intelligence · Computer Science 2025-09-30 Haozhe Wang , Qixin Xu , Che Liu , Junhong Wu , Fangzhen Lin , Wenhu Chen

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essential for the success of RL. We observe that for complex…

Machine Learning · Computer Science 2025-07-08 Shihan Dou , Muling Wu , Jingwen Xu , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO) consistently…

Artificial Intelligence · Computer Science 2026-04-20 Chen Wang , Lai Wei , Yanzhi Zhang , Chenyang Shao , Zedong Dan , Weiran Huang , Ge Lan , Yue Wang

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

Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical success, they exhibit structural mismatches between reward…

Machine Learning · Computer Science 2026-01-09 Aleksandar Fontana , Marco Simoni , Giulio Rossolini , Andrea Saracino , Paolo Mori

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for…

Computation and Language · Computer Science 2026-01-16 Zihan Lin , Xiaohan Wang , Hexiong Yang , Jiajun Chai , Jie Cao , Guojun Yin , Wei Lin , Ran He

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches…

Machine Learning · Computer Science 2025-05-20 Xuerui Su , Liya Guo , Yue Wang , Yi Zhu , Zhiming Ma , Zun Wang , Yuting Liu

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…

Computation and Language · Computer Science 2026-02-05 Zihan Lin , Xiaohan Wang , Jie Cao , Jiajun Chai , Guojun Yin , Wei Lin , Ran He

State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., $\epsilon$-greedy) for exploration, but this method fails on hard exploration tasks like Montezuma's Revenge. To address the challenge of…

Machine Learning · Computer Science 2022-11-21 Eric Chen , Zhang-Wei Hong , Joni Pajarinen , Pulkit Agrawal

Exploration is a crucial and distinctive aspect of reinforcement learning (RL) that remains a fundamental open problem. Several methods have been proposed to tackle this challenge. Commonly used methods inject random noise directly into the…

Machine Learning · Computer Science 2024-11-06 Sebastian Griesbach , Carlo D'Eramo

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

Machine Learning · Computer Science 2026-05-27 Alex Ayoub , Kavosh Asadi , Dale Schuurmans , Csaba Szepesvári , Karim Bouyarmane

Reinforcement Learning (RL) heavily relies on the careful design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term Reinforcement Learning (LTRL) tasks remains a significant challenge. As a…

Machine Learning · Computer Science 2025-06-03 Qi Ju , Falin Hei , Zhemei Fang , Yunfeng Luo

Reinforcement learning from verifiable rewards (RLVR) has emerged as a central technique for improving the reasoning capabilities of large language models. Despite its effectiveness, how response-level rewards translate into token-level…

Machine Learning · Computer Science 2026-05-21 Kaiyi Zhang , Wei Wu , Yankai Lin

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-24 Chang Liu , Ya-Jun Hu , Ying-Ying Gao , Shi-Lei Zhang , Zhen-Hua Ling