English
Related papers

Related papers: Selective Off-Policy Reference Tuning with Plan Gu…

200 papers

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

Computation and Language · Computer Science 2025-06-19 Shang Hong Sim , Tej Deep Pala , Vernon Toh , Hai Leong Chieu , Amir Zadeh , Chuan Li , Navonil Majumder , Soujanya Poria

Reinforcement learning with verifiable rewards (RLVR) has emerged as the leading approach for enhancing reasoning capabilities in large language models. However, it faces a fundamental compute and memory asymmetry: rollout generation is…

Machine Learning · Computer Science 2026-04-23 Yixuan Even Xu , Yash Savani , Fei Fang , J. Zico Kolter

We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer.…

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to…

Artificial Intelligence · Computer Science 2025-10-30 Jiaqi Wang , Kevin Qinghong Lin , James Cheng , Mike Zheng Shou

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Artificial Intelligence · Computer Science 2026-03-06 Anisha Garg , Claire Zhang , Nishit Neema , David Bick , Ganesh Venkatesh , Joel Hestness

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all tokens in a trajectory. Such uniform assignment ignores which…

Artificial Intelligence · Computer Science 2026-05-27 Ankur Samanta , Akshayaa Magesh , Ayush Jain , Youliang Yu , Daniel Jiang , Kavosh Asadi , Kaveh Hassani , Paul Sajda , Jalaj Bhandari , Yonathan Efroni

Reinforcement learning has been widely applied to enhance the reasoning capabilities of large language models. Extending the inference limits of smaller models has become a prominent research focus. However, algorithms such as Group…

Artificial Intelligence · Computer Science 2025-10-10 Hao Wu , Wei Liu

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

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reasoning Models. However, standard outcome-based supervision suffers from a critical…

Artificial Intelligence · Computer Science 2026-03-02 Yanwei Ren , Haotian Zhang , Likang Xiao , Xikai Zhang , Jiaxing Huang , Jiayan Qiu , Baosheng Yu , Quan Chen , Liu Liu

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest…

Artificial Intelligence · Computer Science 2025-08-19 Yongxin Guo , Wenbo Deng , Zhenglin Cheng , Xiaoying Tang

Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merely reinforce what the…

Machine Learning · Computer Science 2026-01-28 Ruiyang Zhou , Shuozhe Li , Amy Zhang , Liu Leqi

We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. Our motivation comes from recent work on off-policy Proximal Policy Optimization (PPO), which improves training stability, sampling…

Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated…

Computation and Language · Computer Science 2025-12-29 Xinyu Tang , Yuliang Zhan , Zhixun Li , Wayne Xin Zhao , Zhenduo Zhang , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts. We propose Prompt…

Machine Learning · Computer Science 2026-03-24 Andrei Baroian , Rutger Berger

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Machine Learning · Computer Science 2026-02-27 Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-quality data for training, which can stabilize RL training and…

Artificial Intelligence · Computer Science 2025-06-04 Haizhong Zheng , Yang Zhou , Brian R. Bartoldson , Bhavya Kailkhura , Fan Lai , Jiawei Zhao , Beidi Chen

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1,…

Machine Learning · Computer Science 2025-06-13 Wei Xiong , Jiarui Yao , Yuhui Xu , Bo Pang , Lei Wang , Doyen Sahoo , Junnan Li , Nan Jiang , Tong Zhang , Caiming Xiong , Hanze Dong

Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the…

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning.…

‹ Prev 1 2 3 10 Next ›