English
Related papers

Related papers: HINT: Helping Ineffective Rollouts Navigate Toward…

200 papers

Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative…

Machine Learning · Computer Science 2026-04-02 Yu Xia , Canwen Xu , Zhewei Yao , Julian McAuley , Yuxiong He

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: the near-miss reward…

Artificial Intelligence · Computer Science 2025-07-04 Kaiyi Zhang , Ang Lv , Jinpeng Li , Yongbo Wang , Feng Wang , Haoyuan Hu , Rui Yan

To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into post-training, which are prefix segments of complete reasoning trajectories, aiming for…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Feng Zhang , Zezhong Tan , Xinhong Ma , Ziqiang Dong , Xi Leng , Jianfei Zhao , Xin Sun , Yang Yang

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Machine Learning · Computer Science 2025-10-21 Mengqi Liao , Xiangyu Xi , Ruinian Chen , Jia Leng , Yangen Hu , Ke Zeng , Shuai Liu , Huaiyu Wan

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the…

Computation and Language · Computer Science 2025-10-15 Arash Marioriyad , Shaygan Adim , Nima Alighardashi , Mahdieh Soleymani Banghshah , Mohammad Hossein Rohban

Current online reinforcement learning (RL) algorithms like GRPO share a key limitation in LLM reasoning: they cannot learn from problems that are "unsolvable" to the model. In other words, they can only improve performance on problems where…

Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time,…

Machine Learning · Computer Science 2026-03-06 Yangzhen Wu , Shanda Li , Zixin Wen , Xin Zhou , Ameet Talwalkar , Yiming Yang , Wenhao Huang , Tianle Cai

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Machine Learning · Computer Science 2025-07-17 Ziru Liu , Cheng Gong , Xinyu Fu , Yaofang Liu , Ran Chen , Shoubo Hu , Suiyun Zhang , Rui Liu , Qingfu Zhang , Dandan Tu

Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform data sampling. While previous work has explored curriculum…

Machine Learning · Computer Science 2025-09-30 Qinsi Wang , Jinghan Ke , Hancheng Ye , Yueqian Lin , Yuzhe Fu , Jianyi Zhang , Kurt Keutzer , Chenfeng Xu , Yiran Chen

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to…

Machine Learning · Computer Science 2025-09-09 Ziheng Li , Zexu Sun , Jinman Zhao , Erxue Min , Yongcheng Zeng , Hui Wu , Hengyi Cai , Shuaiqiang Wang , Dawei Yin , Xu Chen , Zhi-Hong Deng

Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality…

Artificial Intelligence · Computer Science 2025-12-30 Kongcheng Zhang , Qi Yao , Shunyu Liu , Wenjian Zhang , Min Cen , Yang Zhou , Wenkai Fang , Yiru Zhao , Baisheng Lai , Mingli Song

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

Computation and Language · Computer Science 2025-12-15 Mrinal Rawat , Arkajyoti Chakraborty , Neha Gupta , Roberto Pieraccini

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

Computation and Language · Computer Science 2025-04-22 Zihao Feng , Xiaoxue Wang , Ziwei Bai , Donghang Su , Bowen Wu , Qun Yu , Baoxun Wang

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Artificial Intelligence · Computer Science 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off:…

Computation and Language · Computer Science 2026-05-22 Yuchun Fan , Bei Li , Peiguang Li , Yilin Wang , Yongyu Mu , Jian Yang , Xin Chen , Rongxiang Weng , Jingang Wang , Xunliang Cai , Jingbo Zhu , Tong Xiao

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box"…

Computation and Language · Computer Science 2026-04-14 Miaosen Luo , Zhenhao Yang , Jieshen Long , Jinghu Sun , Yichu Liu , Sijie Mai

Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group…

Machine Learning · Computer Science 2026-02-04 Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Yulei Qin , Gang Li , Zongyi Li , Zihan Xu , Yuchen Shi , Zhekai Lin , Xiao Cui , Ke Li , Xing Sun
‹ Prev 1 2 3 10 Next ›