English
Related papers

Related papers: What If We Allocate Test-Time Compute Adaptively?

200 papers

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow…

Machine Learning · Computer Science 2025-09-30 Haoran He , Yuxiao Ye , Qingpeng Cai , Chen Hu , Binxing Jiao , Daxin Jiang , Ling Pan

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental…

Artificial Intelligence · Computer Science 2025-02-05 Ning Dai , Zheng Wu , Renjie Zheng , Ziyun Wei , Wenlei Shi , Xing Jin , Guanlin Liu , Chen Dun , Liang Huang , Lin Yan

Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs). However, most existing RL approaches rely on sparse outcome rewards, which fail to credit correct…

Machine Learning · Computer Science 2026-01-28 Haolin Liu , Dian Yu , Sidi Lu , Yujun Zhou , Rui Liu , Zhenwen Liang , Haitao Mi , Chen-Yu Wei , Dong Yu

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically…

Computation and Language · Computer Science 2026-03-03 Longze Chen , Lu Wang , Renke Shan , Ze Gong , Run Luo , Jiaming Li , Jing Luo , Qiyao Wang , Min Yang

Test-time scaling is a powerful strategy for boosting the performance of large language models on complex reasoning tasks. While state-of-the-art approaches often employ generative verifiers to select the best solution from a pool of…

Artificial Intelligence · Computer Science 2025-10-17 Kyle Montgomery , Sijun Tan , Yuqi Chen , Siyuan Zhuang , Tianjun Zhang , Raluca Ada Popa , Chenguang Wang

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…

Machine Learning · Computer Science 2026-04-23 Jingyi Wang , Lei Zhu , Tengjin Weng , Song-Li Wu , Haochen Tan , Jierun Chen , Chaofan Tao , Haoli Bai , Lu Hou , Lifeng Shang , Xiao-Ping Zhang

Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value function in favor of empirically estimated returns. This hinders test-time compute scaling that relies…

Machine Learning · Computer Science 2026-04-14 Kusha Sareen , Morgane M Moss , Alessandro Sordoni , Rishabh Agarwal , Arian Hosseini

State-of-the-art language models can exhibit impressive reasoning refinement capabilities on math, science or coding tasks. However, recent work demonstrates that even the best models struggle to identify \textit{when and where to refine}…

Computation and Language · Computer Science 2024-06-26 Alex Havrilla , Sharath Raparthy , Christoforus Nalmpantis , Jane Dwivedi-Yu , Maksym Zhuravinskyi , Eric Hambro , Roberta Raileanu

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to…

Machine Learning · Computer Science 2025-08-14 Luca Eyring , Shyamgopal Karthik , Alexey Dosovitskiy , Nataniel Ruiz , Zeynep Akata

Adaptive Computing is an application-agnostic outer loop framework to strategically deploy simulations and experiments to guide decision making for scale-up analysis. Resources are allocated over successive batches, which makes the…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Machine Learning · Computer Science 2025-10-31 Fuxiang Zhang , Jiacheng Xu , Chaojie Wang , Ce Cui , Yang Liu , Bo An

Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority…

Computation and Language · Computer Science 2026-04-24 Peng Kuang , Yanli Wang , Xiaoyu Han , Yaowenqi Liu , Kaidi Xu , Haohan Wang

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive…

Computation and Language · Computer Science 2026-05-22 Farima Fatahi Bayat , Moin Aminnaseri , Pouya Pezeshkpour , Estevam Hruschka

Process reward models (PRMs) rely on high-quality process supervision data, yet existing construction methods often provide limited control over error location, error type, and trajectory consistency. We propose a controllable and…

Artificial Intelligence · Computer Science 2026-05-05 Yinghui Chi , Lucien Wang

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…

Computation and Language · Computer Science 2024-10-04 Rohin Manvi , Anikait Singh , Stefano Ermon

Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics,…

Computation and Language · Computer Science 2026-02-10 Ibraheem Muhammad Moosa , Suhas Lohit , Ye Wang , Moitreya Chatterjee , Wenpeng Yin

Large language models (LLMs) struggle with multi-step reasoning, where inference-time scaling has emerged as a promising strategy for performance improvement. Verifier-guided search outperforms repeated sampling when sample size is limited…

Computation and Language · Computer Science 2025-02-04 Fei Yu , Yingru Li , Benyou Wang

Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). Verifying LLM outputs with an Outcome Reward Model (ORM) is a…

Computation and Language · Computer Science 2024-12-13 Liangchen Luo , Yinxiao Liu , Rosanne Liu , Samrat Phatale , Meiqi Guo , Harsh Lara , Yunxuan Li , Lei Shu , Yun Zhu , Lei Meng , Jiao Sun , Abhinav Rastogi

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Computation and Language · Computer Science 2025-07-16 Pedro Ferreira , Wilker Aziz , Ivan Titov