English
Related papers

Related papers: On the Limits of Test-Time Compute: Sequential Rew…

200 papers

We present a method to find an optimal policy with respect to a reward function for a discounted Markov decision process under general linear temporal logic (LTL) specifications. Previous work has either focused on maximizing a cumulative…

Systems and Control · Electrical Eng. & Systems 2021-03-24 Krishna C. Kalagarla , Rahul Jain , Pierluigi Nuzzo

The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While existing trajectory level exploration methods improve the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Qingtao Yu , Changlin Song , Minghao Sun , Zhengyang Yu , Vinay Kumar Verma , Soumya Roy , Sumit Negi , Hongdong Li , Dylan Campbell

Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However,…

Artificial Intelligence · Computer Science 2026-05-13 Rajarshi Roy , Anirban Majumdar , Ritam Raha , David Parker , Marta Kwiatkowska

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently…

Computation and Language · Computer Science 2025-09-08 Shengyin Sun , Yiming Li , Xing Li , Yingzhao Lian , Weizhe Lin , Hui-Ling Zhen , Zhiyuan Yang , Chen Chen , Xianzhi Yu , Mingxuan Yuan , Chen Ma

A major bottleneck of standard auto-regressive large language models is that their inference process is inherently sequential, resulting in very long and costly inference times. To circumvent this, practitioners proposed a class of language…

Machine Learning · Computer Science 2025-11-11 Sitan Chen , Kevin Cong , Jerry Li

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

Artificial Intelligence · Computer Science 2025-11-11 Jianhao Chen , Zishuo Xun , Bocheng Zhou , Han Qi , Hangfan Zhang , Qiaosheng Zhang , Yang Chen , Wei Hu , Yuzhong Qu , Wanli Ouyang , Shuyue Hu

Many interventions, such as vaccines in clinical trials or coupons in online marketplaces, must be assigned sequentially without full knowledge of their effects. Multi-armed bandit algorithms have proven successful in such settings.…

Machine Learning · Statistics 2026-05-07 Aidan Gleich , Eric Laber , Alexander Volfovsky

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…

Artificial Intelligence · Computer Science 2025-10-27 Yang Zhang , Wenxin Xu , Xiaoyan Zhao , Wenjie Wang , Fuli Feng , Xiangnan He , Tat-Seng Chua

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

Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining. Similarly, Chain-of-Thought (CoT)…

Machine Learning · Computer Science 2025-06-19 Baohao Liao , Hanze Dong , Yuhui Xu , Doyen Sahoo , Christof Monz , Junnan Li , Caiming Xiong

Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…

Computation and Language · Computer Science 2026-03-09 Jianghao Wu , Yasmeen George , Jin Ye , Yicheng Wu , Daniel F. Schmidt , Jianfei Cai

Recent advances have applied large language models (LLMs) to sequential recommendation, leveraging their pre-training knowledge and reasoning capabilities to provide more personalized user experiences. However, existing LLM-based methods…

Computation and Language · Computer Science 2025-08-21 Yutian Liu , Zhengyi Yang , Jiancan Wu , Xiang Wang

Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with verifiable signals. However, due to reward sparsity, effectiveness depends heavily…

Computation and Language · Computer Science 2026-01-27 Sanghwan Bae , Jiwoo Hong , Min Young Lee , Hanbyul Kim , JeongYeon Nam , Donghyun Kwak

Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a…

Computation and Language · Computer Science 2026-04-21 Sangjun Song , Minjae Oh , Seungkyu Lee , Sungmin Jo , Yohan Jo

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Computation and Language · Computer Science 2025-09-23 Xiaohao Liu , Xiaobo Xia , Weixiang Zhao , Manyi Zhang , Xianzhi Yu , Xiu Su , Shuo Yang , See-Kiong Ng , Tat-Seng Chua

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

Computation and Language · Computer Science 2024-11-21 Sean Welleck , Amanda Bertsch , Matthew Finlayson , Hailey Schoelkopf , Alex Xie , Graham Neubig , Ilia Kulikov , Zaid Harchaoui

Recent work has shown that language models can self-improve by maximizing their own confidence in their predictions, without relying on external verifiers or reward signals. In this work, we study the test-time scaling of language models…

Machine Learning · Computer Science 2025-07-25 Matthias Otth , Jonas Hübotter , Ido Hakimi , Andreas Krause

Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although…

Artificial Intelligence · Computer Science 2025-10-01 Yingqian Cui , Zhenwei Dai , Pengfei He , Bing He , Hui Liu , Xianfeng Tang , Jingying Zeng , Suhang Wang , Yue Xing , Jiliang Tang , Benoit Dumoulin

Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…

Machine Learning · Computer Science 2025-12-30 Lei Wang , Zikun Ye , Jinglong Zhao

Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this…

Machine Learning · Computer Science 2026-03-23 Chenruo Liu , Yijun Dong , Yiqiu Shen , Qi Lei