English
Related papers

Related papers: DuaShepherd: Integrating Stepwise Correctness and …

200 papers

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Computation and Language · Computer Science 2026-02-04 Brian Christian , Hannah Rose Kirk , Jessica A. F. Thompson , Christopher Summerfield , Tsvetomira Dumbalska

Machine learning models support decision-making, yet the reasons behind their predictions are opaque. Clear and reliable explanations help users make informed decisions and avoid blindly trusting model outputs. However, many existing…

Logic in Computer Science · Computer Science 2026-03-03 Francisco Mateus Rocha Filho , Ajalmar Rêgo da Rocha Neto , Thiago Alves Rocha

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

Learning Automata (LA) are considered as one of the most powerful tools in the field of reinforcement learning. The family of estimator algorithms is proposed to improve the convergence rate of LA and has made great achievements. However,…

Artificial Intelligence · Computer Science 2017-12-04 Chong Di

Large Language Models (LLMs) have shown remarkable performance in various natural language processing tasks but face challenges in mathematical reasoning, where complex problem-solving requires both linguistic understanding and mathematical…

Computation and Language · Computer Science 2025-03-20 Shuguang Chen , Guang Lin

Large language models (LLMs) are often sycophantic, prioritizing agreement with their users over accurate or objective statements. This problematic behavior becomes more pronounced during reinforcement learning from human feedback (RLHF),…

Artificial Intelligence · Computer Science 2024-12-03 Henry Papadatos , Rachel Freedman

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by…

Computation and Language · Computer Science 2025-03-31 Weizhe Yuan , Richard Yuanzhe Pang , Kyunghyun Cho , Xian Li , Sainbayar Sukhbaatar , Jing Xu , Jason Weston

Tool invocation significantly enhances the capabilities of Large Language Models (LLMs), yet challenges persist, particularly in complex task scenarios. Current methods, such as instruction-enhanced reasoning and supervised fine-tuning,…

Artificial Intelligence · Computer Science 2025-08-07 Yifei Lu , Fanghua Ye , Jian Li , Qiang Gao , Cheng Liu , Haibo Luo , Nan Du , Xiaolong Li , Feiliang Ren

Process supervision enhances the performance of large language models in reasoning tasks by providing feedback at each step of chain-of-thought reasoning. However, due to the lack of effective process supervision methods, even advanced…

Artificial Intelligence · Computer Science 2025-05-15 Jiawei Li , Xinyue Liang , Junlong Zhang , Yizhe Yang , Chong Feng , Yang Gao

Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workflows faces two obstacles: the lack of environments supporting…

Machine Learning · Computer Science 2026-04-08 Cheng Jiayang , Xin Liu , Zhihan Zhang , Haoyang Wen , Zixuan Zhang , Qingyu Yin , Shiyang Li , Priyanka Nigam , Bing Yin , Chao Zhang , Yangqiu Song

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length…

Artificial Intelligence · Computer Science 2025-06-03 Yuliang Liu , Junjie Lu , Zhaoling Chen , Chaofeng Qu , Jason Klein Liu , Chonghan Liu , Zefan Cai , Yunhui Xia , Li Zhao , Jiang Bian , Chuheng Zhang , Wei Shen , Zhouhan Lin

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully…

Machine Learning · Computer Science 2019-02-19 Hao Liu , Alexander Trott , Richard Socher , Caiming Xiong

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulations typically treat exploration and consolidation as a…

Machine Learning · Computer Science 2026-05-15 Wenze Lin , Zhen Yang , Xitai Jiang , Xiaoteng Ma , Gao Huang

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

Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert…

Robotics · Computer Science 2023-10-24 Yuwei Zeng , Yiqing Xu

While reinforcement learning has advanced the reasoning abilities of Large Language Models (LLMs), these gains are largely confined to English, creating a significant performance disparity across languages. To address this, we introduce…

Computation and Language · Computer Science 2025-10-01 Fahim Faisal , Kaiqiang Song , Song Wang , Simin Ma , Shujian Liu , Haoyun Deng , Sathish Reddy Indurthi

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Computation and Language · Computer Science 2026-04-09 Qiyao Ma , Dechen Gao , Rui Cai , Boqi Zhao , Hanchu Zhou , Junshan Zhang , Zhe Zhao

Process Reward Models (PRMs) are crucial for guiding Large Language Models (LLMs) in complex scenarios by providing dense reward signals. However, existing PRMs primarily rely on heuristic approaches, which struggle with cross-domain…

Computation and Language · Computer Science 2025-07-25 Zhangyue Yin , Qiushi Sun , Zhiyuan Zeng , Qinyuan Cheng , Xipeng Qiu , Xuanjing Huang

Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of…

Computation and Language · Computer Science 2024-10-03 Muchen Yang , Moxin Li , Yongle Li , Zijun Chen , Chongming Gao , Junqi Zhang , Yangyang Li , Fuli Feng

Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, the recent LLM-as-a-Judge paradigms enable better and more…

Computation and Language · Computer Science 2026-02-03 Xinyu Hu , Yancheng He , Weixun Wang , Tao Feng , Li Lin , Jiashun Liu , Wenbo Su , Bo Zheng , Xiaojun Wan