English
Related papers

Related papers: TGPO: Tree-Guided Preference Optimization for Robu…

200 papers

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

Recent advancements in large language models (LLMs) have enabled understanding webpage contexts, product details, and human instructions. Utilizing LLMs as the foundational architecture for either reward models or policies in reinforcement…

Machine Learning · Computer Science 2024-08-30 Shuang Feng , Grace Feng

Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF),…

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response…

Computation and Language · Computer Science 2025-03-27 Zhouhong Gu , Xingzhou Chen , Xiaoran Shi , Tao Wang , Suhang Zheng , Tianyu Li , Hongwei Feng , Yanghua Xiao

Reinforcement learning from human feedback (RLHF) has demonstrated great promise in aligning large language models (LLMs) with human preference. Depending on the availability of preference data, both online and offline RLHF are active areas…

Machine Learning · Computer Science 2025-02-20 Shicong Cen , Jincheng Mei , Katayoon Goshvadi , Hanjun Dai , Tong Yang , Sherry Yang , Dale Schuurmans , Yuejie Chi , Bo Dai

Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Ziang Yan , Zhilin Li , Yinan He , Chenting Wang , Kunchang Li , Xinhao Li , Xiangyu Zeng , Zilei Wang , Yali Wang , Yu Qiao , Limin Wang , Yi Wang

Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward…

Artificial Intelligence · Computer Science 2026-03-03 Fanqi Kong , Jiayi Zhang , Mingyi Deng , Chenglin Wu , Yuyu Luo , Bang Liu

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

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

Machine Learning · Computer Science 2026-05-11 Dominik Wagner , Ankit Kanwar , Luke Ong

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement…

Artificial Intelligence · Computer Science 2026-05-29 Shenghao Ye , Yu Guo , Zhengheng Li , Shuangwu Chen , Jian Yang

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…

Computation and Language · Computer Science 2026-05-26 Yihong Tang , Kehai Chen , Liang Yue , Benyou Wang , Min Zhang

A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation…

Machine Learning · Computer Science 2025-10-15 Nianyi Lin , Jiajie Zhang , Lei Hou , Juanzi Li

Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a single response language or rely on a fixed dominant language for…

Computation and Language · Computer Science 2026-05-26 Geyang Guo , Hiromi Wakaki , Yuki Mitsufuji , Alan Ritter , Wei Xu

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods…

Computation and Language · Computer Science 2025-10-13 Xingyu Lin , Yilin Wen , En Wang , Du Su , Wenbin Liu , Chenfu Bao , Zhonghou Lv

Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its superior performance and flexible…

Machine Learning · Computer Science 2026-03-12 Baoheng Zhu , Deyu Bo , Delvin Ce Zhang , Xiao Wang

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

Branch-and-Bound (B\&B) is the dominant exact solution method for Mixed Integer Linear Programs (MILP), yet its exponential time complexity poses significant challenges for large-scale instances. The growing capabilities of machine learning…

Machine Learning · Computer Science 2025-11-18 Abdelouahed Ben Mhamed , Assia Kamal-Idrissi , Amal El Fallah Seghrouchni

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent applications. However, training LLM agents for complex…

Machine Learning · Computer Science 2025-12-09 Hanjiang Hu , Changliu Liu , Na Li , Yebin Wang