English
Related papers

Related papers: Stabilizing Unsupervised Self-Evolution of MLLMs v…

200 papers

Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensions improve upon vanilla RLVR (e.g., GRPO) by providing…

Artificial Intelligence · Computer Science 2026-04-21 Ziqi Zhao , Zhaochun Ren , Jiahong Zou , Liu Yang , Zhiwei Xu , Xuri Ge , Zhumin Chen , Xinyu Ma , Daiting Shi , Shuaiqiang Wang , Dawei Yin , Xin Xin

Reinforcement Learning with Verifiable Rewards~(RLVR) has emerged as a powerful learn-to-reason paradigm for large reasoning models to tackle complex tasks. However, the current RLVR paradigm is still not efficient enough, as it works in a…

Computation and Language · Computer Science 2026-03-10 Junjie Zhang , Guozheng Ma , Shunyu Liu , Haoyu Wang , Jiaxing Huang , Ting-En Lin , Fei Huang , Yongbin Li , Dacheng Tao

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle…

Artificial Intelligence · Computer Science 2025-05-22 Guanghao Zhou , Panjia Qiu , Cen Chen , Jie Wang , Zheming Yang , Jian Xu , Minghui Qiu

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Computation and Language · Computer Science 2025-07-30 Carel van Niekerk , Renato Vukovic , Benjamin Matthias Ruppik , Hsien-chin Lin , Milica Gašić

Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…

Computation and Language · Computer Science 2023-08-07 Chenglong Wang , Hang Zhou , Yimin Hu , Yifu Huo , Bei Li , Tongran Liu , Tong Xiao , Jingbo Zhu

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Machine Learning · Computer Science 2025-05-20 Qingyang Zhang , Haitao Wu , Changqing Zhang , Peilin Zhao , Yatao Bian

Training large reasoning models (LRMs) with reinforcement learning in STEM domains is hindered by the scarcity of high-quality, diverse, and verifiable problem sets. Existing synthesis methods, such as Chain-of-Thought prompting, often…

Artificial Intelligence · Computer Science 2025-05-27 Xiong Jun Wu , Zhenduo Zhang , ZuJie Wen , Zhiqiang Zhang , Wang Ren , Lei Shi , Cai Chen , Deng Zhao , Qing Wang , Xudong Han , Chengfu Tang , Dingnan Jin , Qing Cui , Jun Zhou

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Computation and Language · Computer Science 2024-06-18 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Junchen Wan , Fuzheng Zhang , Di Zhang , Ji-Rong Wen

Online reinforcement learning (RL) algorithms are often difficult to deploy in complex human-facing applications as they may learn slowly and have poor early performance. To address this, we introduce a practical algorithm for incorporating…

Artificial Intelligence · Computer Science 2022-01-03 Tong Mu , Georgios Theocharous , David Arbour , Emma Brunskill

In nature, the behaviors of many complex systems can be described by parsimonious math equations. Automatically distilling these equations from limited data is cast as a symbolic regression process which hitherto remains a grand challenge.…

Machine Learning · Computer Science 2023-05-25 Yilong Xu , Yang Liu , Hao Sun

Recent AI advancements, such as OpenAI's new models, are transforming LLMs into LRMs (Large Reasoning Models) that perform reasoning during inference, taking extra time and compute for higher-quality outputs. We aim to uncover the…

Artificial Intelligence · Computer Science 2025-02-11 Guanghao Ye , Khiem Duc Pham , Xinzhi Zhang , Sivakanth Gopi , Baolin Peng , Beibin Li , Janardhan Kulkarni , Huseyin A. Inan

Stochastic control-flow models (SCFMs) are a class of generative models that involve branching on choices from discrete random variables. Amortized gradient-based learning of SCFMs is challenging as most approaches targeting discrete…

Machine Learning · Statistics 2019-09-17 Tuan Anh Le , Adam R. Kosiorek , N. Siddharth , Yee Whye Teh , Frank Wood

Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. However, in many reasoning domains, the model must also validate generated tasks and…

Artificial Intelligence · Computer Science 2026-05-28 Bowen Wei , Nan Wang , Yuqing Zhou , Jinhao Pan , Ziwei Zhu

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

Recent Large Reasoning Language Models (LRLMs) employ long chain-of-thought reasoning with complex reflection behaviors, typically signaled by specific trigger words (e.g., "Wait" and "Alternatively") to enhance performance. However, these…

Computation and Language · Computer Science 2025-11-18 Jiameng Huang , Baijiong Lin , Guhao Feng , Jierun Chen , Di He , Lu Hou

Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Congzhi Zhang , Jiawei Peng , Zhenglin Wang , Yilong Lai , Haowen Sun , Heng Chang , Fei Ma , Weijiang Yu

Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold supervision, such as ground-truth answers, which is…

Artificial Intelligence · Computer Science 2026-04-15 Sohyun An , Shuibenyang Yuan , Hayeon Lee , Cho-Jui Hsieh , Alexander Min

Reinforcement learning (RL) is rapidly reaching and surpassing human-level control capabilities. However, state-of-the-art RL algorithms often require timesteps and reaction times significantly faster than human capabilities, which is…

Machine Learning · Computer Science 2025-07-29 Devdhar Patel , Hava Siegelmann

Post-training improves instruction-following and helpfulness of large language models (LLMs) but often reduces generation diversity, which leads to repetitive outputs in open-ended settings, a phenomenon known as mode collapse. Motivated by…

Computation and Language · Computer Science 2026-02-09 Bowen Zhang , Meiyi Wang , Harold Soh

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Machine Learning · Computer Science 2025-09-30 Xingwu Chen , Tianle Li , Difan Zou
‹ Prev 1 4 5 6 7 8 10 Next ›