English
Related papers

Related papers: Process Reinforcement through Implicit Rewards

200 papers

While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions.…

Artificial Intelligence · Computer Science 2025-06-06 Lingxiao Du , Fanqing Meng , Zongkai Liu , Zhixiang Zhou , Ping Luo , Qiaosheng Zhang , Wenqi Shao

Reinforcement Learning from Human Feedback (RLHF) has been credited as the key advance that has allowed Large Language Models (LLMs) to effectively follow instructions and produce useful assistance. Classically, this involves generating…

Machine Learning · Computer Science 2024-02-02 Alex J. Chan , Hao Sun , Samuel Holt , Mihaela van der Schaar

In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. This is evidenced by a high incidence of false positives-solutions that reach the…

Computation and Language · Computer Science 2026-04-20 Youliang Yuan , Qiuyang Mang , Jingbang Chen , Hong Wan , Xiaoyuan Liu , Junjielong Xu , Jen-tse Huang , Wenxuan Wang , Wenxiang Jiao , Pinjia He

Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically…

Artificial Intelligence · Computer Science 2025-11-12 Hieu Tran , Zonghai Yao , Nguyen Luong Tran , Zhichao Yang , Feiyun Ouyang , Shuo Han , Razieh Rahimi , Hong Yu

Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are…

Computation and Language · Computer Science 2025-04-02 Yi Su , Dian Yu , Linfeng Song , Juntao Li , Haitao Mi , Zhaopeng Tu , Min Zhang , Dong Yu

Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors),…

Machine Learning · Computer Science 2020-02-04 Jingkang Wang , Yang Liu , Bo Li

The Process Reward Model (PRM) plays a crucial role in mathematical reasoning tasks, requiring high-quality supervised process data. However, we observe that reasoning steps generated by Large Language Models (LLMs) often fail to exhibit…

Artificial Intelligence · Computer Science 2025-08-25 Yulan Hu , Sheng Ouyang , Jinman Zhao , Yong Liu

We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models. Since post-training LLMs via RL…

Machine Learning · Computer Science 2025-10-02 Zhaolin Gao , Joongwon Kim , Wen Sun , Thorsten Joachims , Sid Wang , Richard Yuanzhe Pang , Liang Tan

Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…

Machine Learning · Computer Science 2025-06-26 Yanzhi Zhang , Zhaoxi Zhang , Haoxiang Guan , Yilin Cheng , Yitong Duan , Chen Wang , Yue Wang , Shuxin Zheng , Jiyan He

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation.…

Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of…

Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…

Machine Learning · Computer Science 2025-07-02 Chenyang Cao , Miguel Rogel-García , Mohamed Nabail , Xueqian Wang , Nicholas Rhinehart

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Machine Learning · Computer Science 2024-09-12 Yifei He , Haoxiang Wang , Ziyan Jiang , Alexandros Papangelis , Han Zhao

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on…

Robotics · Computer Science 2025-12-02 Ruiqi Wang , Dezhong Zhao , Ziqin Yuan , Tianyu Shao , Guohua Chen , Dominic Kao , Sungeun Hong , Byung-Cheol Min

Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. However, existing approaches face a fundamental credit assignment problem: methods like…

Computation and Language · Computer Science 2026-04-02 Chris Samarinas , Haw-Shiuan Chang , Hamed Zamani

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning…

Artificial Intelligence · Computer Science 2026-03-24 Tian Liang , Wenxiang Jiao , Zhiwei He , Jiahao Xu , Haitao Mi , Dong Yu

(This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.) To improve the efficiency of deep reinforcement learning (DRL)-based…

Artificial Intelligence · Computer Science 2021-05-25 Gang Peng , Jin Yang , Xinde Lia , Mohammad Omar Khyam

Large language models (LLMs) are increasingly deployed as intelligent tutoring systems, yet research on optimizing LLMs specifically for educational contexts remains limited. Recent works have proposed reinforcement learning approaches for…

Computation and Language · Computer Science 2026-01-22 Unggi Lee , Jiyeong Bae , Jaehyeon Park , Haeun Park , Taejun Park , Younghoon Jeon , Sungmin Cho , Junbo Koh , Yeil Jeong , Gyeonggeon Lee

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically…

Computation and Language · Computer Science 2026-03-03 Longze Chen , Lu Wang , Renke Shan , Ze Gong , Run Luo , Jiaming Li , Jing Luo , Qiyao Wang , Min Yang