English
Related papers

Related papers: PRPO: Aligning Process Reward with Outcome Reward …

200 papers

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

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

Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the…

Computation and Language · Computer Science 2026-05-08 Mingwei Xu , Hao Fang

Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…

Machine Learning · Computer Science 2025-12-23 Bilal Faye , Hanane Azzag , Mustapha Lebbah

Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational…

Machine Learning · Computer Science 2025-07-04 Wu Fei , Hao Kong , Shuxian Liang , Yang Lin , Yibo Yang , Jing Tang , Lei Chen , Xiansheng Hua

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong…

Computation and Language · Computer Science 2025-11-10 Chenxi Liu , Junjie Liang , Yuqi Jia , Bochuan Cao , Yang Bai , Heng Huang , Xun Chen

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

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

Multi-turn tool calling is challenging for Large Language Models (LLMs) because rewards are sparse and exploration is expensive. A common recipe, SFT followed by GRPO, can stall when within-group reward variation is low (e.g., more rollouts…

Artificial Intelligence · Computer Science 2026-02-04 Haitian Zhong , Jixiu Zhai , Lei Song , Jiang Bian , Qiang Liu , Tieniu Tan

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

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

Prompt optimization is a practical and widely applicable alternative to fine tuning for improving large language model performance. Yet many existing methods evaluate candidate prompts by sampling full outputs, often coupled with self…

Computation and Language · Computer Science 2025-09-19 Chenzhuo Zhao , Ziqian Liu , Xinda Wang , Junting Lu , Chaoyi Ruan

Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer from unstable policy…

Computation and Language · Computer Science 2025-10-21 Yuzhong Zhao , Yue Liu , Junpeng Liu , Jingye Chen , Xun Wu , Yaru Hao , Tengchao Lv , Shaohan Huang , Lei Cui , Qixiang Ye , Fang Wan , Furu Wei

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

Artificial Intelligence · Computer Science 2026-03-17 Zhijie Wang

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

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Computation and Language · Computer Science 2024-10-23 Alexander G. Padula , Dennis J. N. J. Soemers

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Artificial Intelligence · Computer Science 2026-04-13 Tianyi Wang , Yixia Li , Long Li , Yibiao Chen , Shaohan Huang , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants…

Artificial Intelligence · Computer Science 2026-04-21 Zhaokang Liao , Yingguo Gao , Yi Yang , Yongheng Hu , Jingting Ding

Group Relative Policy Optimization (GRPO) is widely used for critic-free Large Language Model (LLM) post-training, but its KL regularization is usually implemented as a local loss-side token penalty. We show that this misses the…

Machine Learning · Computer Science 2026-05-26 Jiarui Yao , Ruida Wang , Hao Bai , Tong Zhang

Recent advances in Large Language Models (LLMs) have transformed text-to-speech (TTS) synthesis, inspiring autoregressive frameworks that represent speech as sequences of discrete codec tokens. Among them, single-codebook TTS LLMs have…

Sound · Computer Science 2025-11-27 Yicheng Zhong , Peiji Yang , Zhisheng Wang