English
Related papers

Related papers: More Bang for the Buck: Process Reward Modeling wi…

200 papers

Semi-supervised learning has emerged as an appealing strategy to train deep models with limited supervision. Most prior literature under this learning paradigm resorts to dual-based architectures, typically composed of a teacher-student…

Computer Vision and Pattern Recognition · Computer Science 2022-03-08 Martin Van Waerebeke , Gregory Lodygensky , Jose Dolz

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit…

Artificial Intelligence · Computer Science 2026-04-21 Benteng Chen , Weida Wang , Shufei Zhang , Mingbao Lin , Min Zhang

Large Language Models have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to…

Computation and Language · Computer Science 2026-05-26 Hang Yan , Fangzhi Xu , Rongman Xu , Yifei Li , Jian Zhang , Haoran Luo , Xiaobao Wu , Luu Anh Tuan , Haiteng Zhao , Qika Lin , Jun Liu

Despite recent advances in AI, the development of systems capable of executing complex, multi-step reasoning tasks involving multiple tools remains a significant challenge. Current benchmarks fall short in capturing the real-world…

Computation and Language · Computer Science 2025-01-03 Vaskar Nath , Pranav Raja , Claire Yoon , Sean Hendryx

While online Reinforcement Learning has emerged as a crucial technique for aligning flow matching models with human preferences, current approaches are hindered by inefficient exploration during training rollouts. Relying on undirected…

Machine Learning · Computer Science 2026-02-09 Ruizhe Zhong , Jiesong Lian , Xiaoyue Mi , Zixiang Zhou , Yuan Zhou , Qinglin Lu , Junchi Yan

Reinforcement learning with verifiable rewards (RLVR) has advanced reasoning capabilities in multimodal large language models. However, existing methods typically treat visual inputs as deterministic, overlooking the perceptual ambiguity…

Artificial Intelligence · Computer Science 2026-01-16 Rui Liu , Dian Yu , Tong Zheng , Runpeng Dai , Zongxia Li , Wenhao Yu , Zhenwen Liang , Linfeng Song , Haitao Mi , Pratap Tokekar , Dong Yu

External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an auxiliary process reward model (PRM) is used to score and…

Machine Learning · Computer Science 2025-05-26 Zeen Song , Wenwen Qiang , Siyu Zhao , Changwen Zheng , Gang Hua

This paper questions the effectiveness of a modern predictive uncertainty quantification approach, called \emph{evidential deep learning} (EDL), in which a single neural network model is trained to learn a meta distribution over the…

Machine Learning · Computer Science 2024-11-04 Maohao Shen , J. Jon Ryu , Soumya Ghosh , Yuheng Bu , Prasanna Sattigeri , Subhro Das , Gregory W. Wornell

Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this work, we present a novel technique, named Error-Driven Uncertainty Aware Training (EUAT), which aims to enhance…

Machine Learning · Computer Science 2024-09-12 Pedro Mendes , Paolo Romano , David Garlan

In the study of complex systems, evaluating physical observables often requires sampling representative configurations via Monte Carlo techniques. These methods rely on repeated evaluations of the system's energy and force fields, which can…

Disordered Systems and Neural Networks · Physics 2025-07-02 Dimitrios Tzivrailis , Alberto Rosso , Eiji Kawasaki

Multimodal large language models (MLLMs) still perform poorly on scientific tasks, particularly those requiring multi-step and interpretable reasoning. Their limitations include insufficient scientific reasoning patterns, lack of global…

Artificial Intelligence · Computer Science 2025-07-15 Chenglin Zhu , Tao Zhang , Chong Li , Mingan Lin , Zenan Zhou , Jian Xie

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all…

Machine Learning · Computer Science 2026-04-06 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Machine Learning · Computer Science 2026-02-04 Ruiyi Ding , Yongxuan Lv , Xianhui Meng , Jiahe Song , Chao Wang , Chen Jiang , Yuan Cheng

Reward machines (RMs) provide a structured way to specify non-Markovian rewards in reinforcement learning (RL), thereby improving both expressiveness and programmability. Viewed more broadly, they separate what is known about the…

Machine Learning · Computer Science 2025-08-21 Daniel Ajeleye , Ashutosh Trivedi , Majid Zamani

Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based "Think step by step" approaches, the field has evolved in two main…

Computation and Language · Computer Science 2025-07-25 Andreea Nica , Ivan Zakazov , Nicolas Mario Baldwin , Saibo Geng , Robert West

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where…

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined…

Machine Learning · Computer Science 2018-03-02 Vladimir Feinberg , Alvin Wan , Ion Stoica , Michael I. Jordan , Joseph E. Gonzalez , Sergey Levine

Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is…

Machine Learning · Computer Science 2026-01-08 Jing-Cheng Pang , Liu Sun , Chang Zhou , Xian Tang , Haichuan Ma , Kun Jiang , Jianlong Wang , Kai Zhang , Sijie Wu , Haoran Cai , Chenwei Wu , Xubin Li , Xin Chen

Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack,…

Machine Learning · Computer Science 2022-09-16 Yue Wang , Fei Miao , Shaofeng Zou