English
Related papers

Related papers: Reasoning without Regret

200 papers

In this work, we study the learning theory of reward modeling with pairwise comparison data using deep neural networks. We establish a novel non-asymptotic regret bound for deep reward estimators in a non-parametric setting, which depends…

Machine Learning · Statistics 2025-05-13 Yuanhang Luo , Yeheng Ge , Ruijian Han , Guohao Shen

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking…

Computation and Language · Computer Science 2026-03-23 Taiqiang Wu , Zenan Xu , Bo Zhou , Ngai Wong

Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant LLM-as-a-Judge paradigm relies on the strong reasoning capabilities of large models, while…

Computation and Language · Computer Science 2026-02-26 Yike Wang , Faeze Brahman , Shangbin Feng , Teng Xiao , Hannaneh Hajishirzi , Yulia Tsvetkov

Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of…

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Machine Learning · Computer Science 2026-01-16 Chaitanya Kharyal , Calarina Muslimani , Matthew E. Taylor

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous…

Machine Learning · Statistics 2023-11-27 Jianqing Fan , Zhaoran Wang , Zhuoran Yang , Chenlu Ye

Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time…

Computation and Language · Computer Science 2026-02-12 Jiachun Li , Pengfei Cao , Zhuoran Jin , Yubo Chen , Jiexin Xu , Huaijun Li , Xiaojian Jiang , Kang Liu , Jun Zhao

As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison…

Artificial Intelligence · Computer Science 2026-05-12 Pratik Jayarao , Himanshu Gupta , Neeraj Varshney , Chaitanya Dwivedi

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

Artificial Intelligence · Computer Science 2025-10-01 Gang Li , Yulei Qin , Xiaoyu Tan , Dingkang Yang , Yuchen Shi , Zihan Xu , Xiang Li , Xing Sun , Ke Li

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Machine Learning · Computer Science 2025-08-01 Tao He , Rongchuan Mu , Lizi Liao , Yixin Cao , Ming Liu , Bing Qin

Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or…

Computation and Language · Computer Science 2026-05-25 Sirui Chen , Lei Xu , Yuying Zhao , Yutian Chen , Yu Wang , Beier Zhu , Hanwang Zhang , Shengjie Zhao , Chaochao Lu

Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). However, prevailing algorithms like GRPO broadcast a uniform advantage signal…

Artificial Intelligence · Computer Science 2026-04-17 Can Xie , Ruotong Pan , Xiangyu Wu , Yunfei Zhang , Jiayi Fu , Tingting Gao , Guorui Zhou

Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of…

Computation and Language · Computer Science 2025-05-26 Qi Zhang , Shouqing Yang , Lirong Gao , Hao Chen , Xiaomeng Hu , Jinglei Chen , Jiexiang Wang , Sheng Guo , Bo Zheng , Haobo Wang , Junbo Zhao

Process Reward Models (PRMs) have achieved strong results in complex reasoning, but are bottlenecked by costly process-level supervision. A widely used alternative, Monte Carlo Estimation (MCE), defines process rewards as the probability…

Computation and Language · Computer Science 2026-01-21 Bin Xie , Bingbing Xu , Xueyun Tian , Yilin Chen , Huawei Shen

Reward models can significantly enhance the reasoning capabilities of large language models (LLMs), but they typically require extensive curated data and costly training. To mitigate these challenges, training-free approaches such as…

Artificial Intelligence · Computer Science 2025-10-16 He Du , Bowen Li , Chengxing Xie , Chang Gao , Kai Chen , Dacheng Tao

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Artificial Intelligence · Computer Science 2024-10-24 Muhan Lin , Shuyang Shi , Yue Guo , Behdad Chalaki , Vaishnav Tadiparthi , Ehsan Moradi Pari , Simon Stepputtis , Joseph Campbell , Katia Sycara

Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…

Artificial Intelligence · Computer Science 2026-03-06 Minjune Hwang , Yigit Korkmaz , Daniel Seita , Erdem Bıyık

Reinforcement learning algorithms typically assume rewards to be sampled from light-tailed distributions, such as Gaussian or bounded. However, a wide variety of real-world systems generate rewards that follow heavy-tailed distributions. We…

Machine Learning · Computer Science 2021-02-26 Vincent Zhuang , Yanan Sui