English
Related papers

Related papers: Bradley-Terry Policy Optimization for Generative P…

200 papers

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Machine Learning · Computer Science 2025-02-20 Wang Yang , Hongye Jin , Jingfeng Yang , Vipin Chaudhary , Xiaotian Han

Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible…

Artificial Intelligence · Computer Science 2025-12-09 Jindi Lv , Yuhao Zhou , Zheng Zhu , Xiaofeng Wang , Guan Huang , Jiancheng Lv

Recent advances in audio-based generative language models have accelerated AI-driven lyric-to-song generation. However, these models frequently suffer from content hallucination, producing outputs misaligned with the input lyrics and…

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Computation and Language · Computer Science 2026-03-17 Haoyuan Wu , Hai Wang , Jiajia Wu , Jinxiang Ou , Keyao Wang , Weile Chen , Zihao Zheng , Bei Yu

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same…

Computation and Language · Computer Science 2026-02-06 Hongze Tan , Zihan Wang , Jianfei Pan , Jinghao Lin , Hao Wang , Yifan Wu , Tao Chen , Zhihang Zheng , Zhihao Tang , Haihua Yang

Generative models, particularly diffusion models, have achieved remarkable success in density estimation for multimodal data, drawing significant interest from the reinforcement learning (RL) community, especially in policy modeling in…

Machine Learning · Computer Science 2024-12-03 Jinouwen Zhang , Rongkun Xue , Yazhe Niu , Yun Chen , Jing Yang , Hongsheng Li , Yu Liu

Reinforcement learning (RL) involves sequential decision making in uncertain environments. The aim of the decision-making agent is to maximize the benefit of acting in its environment over an extended period of time. Finding an optimal…

Artificial Intelligence · Computer Science 2007-05-23 Istvan Szita , Balint Takacs , Andras Lorincz

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Computation and Language · Computer Science 2026-05-12 Ömer Faruk Akgül , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer…

Machine Learning · Computer Science 2026-03-19 Yuxiang Ji , Ziyu Ma , Yong Wang , Guanhua Chen , Xiangxiang Chu , Liaoni Wu

We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer,…

Machine Learning · Computer Science 2026-01-13 Wang Zixian

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Machine Learning · Computer Science 2026-02-04 Xiangxiang Chu , Hailang Huang , Xiao Zhang , Fei Wei , Yong Wang

Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is…

Machine Learning · Computer Science 2019-12-13 Lior Shani , Yonathan Efroni , Shie Mannor

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents' behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods…

Machine Learning · Computer Science 2024-07-08 Xiao Hu , Jianxiong Li , Xianyuan Zhan , Qing-Shan Jia , Ya-Qin Zhang

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Computation and Language · Computer Science 2025-10-13 Shi-Qi Yan , Quan Liu , Zhen-Hua Ling

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for…

Computation and Language · Computer Science 2026-02-03 Junjie Lu , Yuliang Liu , Chaofeng Qu , Wei Shen , Zhouhan Lin , Chuheng Zhang , Min Xu

Recent advances in reasoning with large language models (LLMs) have shown the effectiveness of Monte Carlo Tree Search (MCTS) for generating high quality intermediate trajectories, particularly in math and symbolic domains. Inspired by…

Artificial Intelligence · Computer Science 2025-12-23 Bingning Huang , Tu Nguyen , Matthieu Zimmer

Recent work reports gains in neural text-to-speech (TTS) with Group Relative Policy Optimization (GRPO). However, in the absence of a verifiable reward for \textit{prosody}, GRPO trained on transcription-oriented signals (CER/NLL) lowers…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Seungyoun Shin , Dongha Ahn , Jiwoo Kim , Sungwook Jeon

Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reasoning regardless of problem complexity. We present…

Artificial Intelligence · Computer Science 2025-08-08 Shangke Lyu , Linjuan Wu , Yuchen Yan , Xingyu Wu , Hao Li , Yongliang Shen , Peisheng Jiang , Weiming Lu , Jun Xiao , Yueting Zhuang

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligning large language…

Machine Learning · Computer Science 2025-06-18 Mingkang Zhu , Xi Chen , Zhongdao Wang , Bei Yu , Hengshuang Zhao , Jiaya Jia