English
Related papers

Related papers: How Reinforcement Learning After Next-Token Predic…

200 papers

The desire to make applications and machines more intelligent and the aspiration to enable their operation without human interaction have been driving innovations in neural networks, deep learning, and other machine learning techniques.…

Machine Learning · Computer Science 2022-09-30 Fadi AlMahamid , Katarina Grolinger

Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often sequentially aggregated reward, are often inherently…

Machine Learning · Computer Science 2019-09-06 Ameer Haj-Ali , Nesreen K. Ahmed , Ted Willke , Joseph Gonzalez , Krste Asanovic , Ion Stoica

Reinforcement learning has recently gained traction as a means to improve combinatorial optimization methods, yet its effectiveness within local search metaheuristics specifically remains comparatively underexamined. In this study, we…

Machine Learning · Computer Science 2026-01-14 Yannick Molinghen , Augustin Delecluse , Renaud De Landtsheer , Stefano Michelini

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

Computation and Language · Computer Science 2021-01-13 Evgeny Lagutin , Daniil Gavrilov , Pavel Kalaidin

Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, reinforcement learning for LLMs faces substantial data scarcity challenges,…

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

We introduce a theorem proving algorithm that uses practically no domain heuristics for guiding its connection-style proof search. Instead, it runs many Monte-Carlo simulations guided by reinforcement learning from previous proof attempts.…

Artificial Intelligence · Computer Science 2018-05-22 Cezary Kaliszyk , Josef Urban , Henryk Michalewski , Mirek Olšák

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2026-03-03 Athul Radhakrishnan , Siddhant Mohan , Mahima Sachdeva

Large language models (LLMs) has experienced exponential growth, they demonstrate remarkable performance across various tasks. Notwithstanding, contemporary research primarily centers on enhancing the size and quality of pretraining data,…

Programming Languages · Computer Science 2024-04-16 Mengnan Qi , Yufan Huang , Yongqiang Yao , Maoquan Wang , Bin Gu , Neel Sundaresan

Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy…

Machine Learning · Computer Science 2026-04-20 Hanbing Liu , Lang Cao , Yuanyi Ren , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yi Chen , Yuying Ge , Rui Wang , Yixiao Ge , Lu Qiu , Ying Shan , Xihui Liu

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that…

Machine Learning · Computer Science 2025-08-11 Rosie Zhao , Alexandru Meterez , Sham Kakade , Cengiz Pehlevan , Samy Jelassi , Eran Malach

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

Machine Learning · Computer Science 2018-06-01 Ju Xu , Zhanxing Zhu

Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement…

Machine Learning · Computer Science 2026-03-24 Ian Wu , Yuxiao Qu , Amrith Setlur , Aviral Kumar

Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment…

Machine Learning · Computer Science 2025-12-09 Ming Chen , Sheng Tang , Rong-Xi Tan , Ziniu Li , Jiacheng Chen , Ke Xue , Chao Qian

Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL…

Computation and Language · Computer Science 2022-10-07 Asaf Yehudai , Leshem Choshen , Lior Fox , Omri Abend

Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…

Machine Learning · Computer Science 2025-03-11 Jeongyeol Kwon , Liu Yang , Robert Nowak , Josiah Hanna

Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…

Machine Learning · Computer Science 2026-01-21 Quy-Anh Dang , Chris Ngo

Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The…

Machine Learning · Computer Science 2019-07-01 Weichang Wu , Junchi Yan , Xiaokang Yang , Hongyuan Zha

LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it…

Software Engineering · Computer Science 2025-10-01 Xunzhu Tang , Iyiola Emmanuel Olatunji , Tiezhu Sun , Jacques Klein , Tegawende F. Bissyande