中文
相关论文

相关论文: A Survey of Process Reward Models: From Outcome Si…

200 篇论文

Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…

计算与语言 · 计算机科学 2025-06-09 Zhuohao Yu , Weizheng Gu , Yidong Wang , Xingru Jiang , Zhengran Zeng , Jindong Wang , Wei Ye , Shikun Zhang

Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing approaches, represented by process reward models (PRMs),…

计算与语言 · 计算机科学 2025-03-07 Wenxiang Chen , Wei He , Zhiheng Xi , Honglin Guo , Boyang Hong , Jiazheng Zhang , Rui Zheng , Nijun Li , Tao Gui , Yun Li , Qi Zhang , Xuanjing Huang

Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited…

计算与语言 · 计算机科学 2025-04-08 Jian Zhao , Runze Liu , Kaiyan Zhang , Zhimu Zhou , Junqi Gao , Dong Li , Jiafei Lyu , Zhouyi Qian , Biqing Qi , Xiu Li , Bowen Zhou

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

机器学习 · 计算机科学 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

机器学习 · 计算机科学 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin

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.…

人工智能 · 计算机科学 2025-06-06 Lingxiao Du , Fanqing Meng , Zongkai Liu , Zhixiang Zhou , Ping Luo , Qiaosheng Zhang , Wenqi Shao

Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during…

计算与语言 · 计算机科学 2025-07-01 Mingyang Song , Zhaochen Su , Xiaoye Qu , Jiawei Zhou , Yu Cheng

Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-based filtered expectation-maximization (FEM) objective for…

机器学习 · 计算机科学 2026-02-03 Junghyun Lee , Branislav Kveton , Anup Rao , Subhojyoti Mukherjee , Ryan A. Rossi , Sunav Choudhary , Alexa Siu

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with images paradigm has emerged, enabling models to dynamically edit…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Yujin Zhou , Pengcheng Wen , Jiale Chen , Boqin Yin , Han Zhu , Jiaming Ji , Juntao Dai , Chi-Min Chan , Sirui Han

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…

计算与语言 · 计算机科学 2026-03-03 Longze Chen , Lu Wang , Renke Shan , Ze Gong , Run Luo , Jiaming Li , Jing Luo , Qiyao Wang , Min Yang

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…

计算与语言 · 计算机科学 2025-07-25 Zhangyue Yin , Qiushi Sun , Zhiyuan Zeng , Qinyuan Cheng , Xipeng Qiu , Xuanjing Huang

Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated. Specifically, they tend to…

机器学习 · 统计学 2025-11-10 Young-Jin Park , Kristjan Greenewald , Kaveh Alim , Hao Wang , Navid Azizan

Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning…

机器学习 · 计算机科学 2025-11-05 Qi Cao , Ruiyi Wang , Ruiyi Zhang , Sai Ashish Somayajula , Pengtao Xie

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

人工智能 · 计算机科学 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep…

机器学习 · 计算机科学 2026-05-22 Xinquan Chen , Chongying Yue , Bangwei Liu , Xuhong Wang , Yingchun Wang , Chaochao Lu

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…

机器学习 · 计算机科学 2024-11-28 Jiaxuan Gao , Shusheng Xu , Wenjie Ye , Weilin Liu , Chuyi He , Wei Fu , Zhiyu Mei , Guangju Wang , Yi Wu

Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). Verifying LLM outputs with an Outcome Reward Model (ORM) is a…

Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their integration into multimodal reasoning remains largely…

计算与语言 · 计算机科学 2025-10-07 Ruilin Luo , Zhuofan Zheng , Yifan Wang , Xinzhe Ni , Zicheng Lin , Songtao Jiang , Yiyao Yu , Chufan Shi , Lei Wang , Ruihang Chu , Jin Zeng , Yujiu Yang

Large language models (LLM) have revolutionized the processing of natural language. Although first benchmarks of the process modeling abilities of LLM are promising, it is currently under debate to what extent an LLM can generate good…

计算与语言 · 计算机科学 2025-03-19 Peter Fettke , Constantin Houy

While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine…

计算与语言 · 计算机科学 2026-02-20 Haotong Yang , Zitong Wang , Shijia Kang , Siqi Yang , Wenkai Yu , Xu Niu , Yike Sun , Yi Hu , Zhouchen Lin , Muhan Zhang