English
Related papers

Related papers: CORE: Contrastive Reflection Enables Rapid Improve…

200 papers

Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration…

Artificial Intelligence · Computer Science 2026-01-30 Kshitij Mishra , Mirat Aubakirov , Martin Takac , Nils Lukas , Salem Lahlou

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…

Artificial Intelligence · Computer Science 2026-05-08 Zijun Gao , Zhikun Xu , Xiao Ye , Ben Zhou

Large language models (LLMs) struggle in knowledge-intensive tasks, as retrievers often overfit to surface similarity and fail on queries involving complex logical relations. The capacity for logical analysis is inherent in model…

Computation and Language · Computer Science 2026-02-03 Wenxuan Zhang , Yuan-Hao Jiang , Changyong Qi , Rui Jia , Yonghe Wu

Automatic prompt optimization has recently emerged as a strategy for improving the quality of prompts used in Large Language Models (LLMs), with the goal of generating more accurate and useful responses. However, most prior work focuses on…

Computation and Language · Computer Science 2025-10-06 Juhyeon Lee , Wonduk Seo , Hyunjin An , Seunghyun Lee , Yi Bu

Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually…

Machine Learning · Computer Science 2026-03-17 Yongxin Wang , Zhicheng Yang , Meng Cao , Mingfei Han , Haokun Lin , Yingying Zhu , Xiaojun Chang , Xiaodan Liang

Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…

Computation and Language · Computer Science 2025-12-11 Vishwas Hegde , Vindhya Shigehalli

Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by directly optimizing correctness, rather than relying solely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Minbin Huang , Runhui Huang , Chuanyang Zheng , Jingyao Li , Guoxuan Chen , Han Shi , Hong Cheng

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy:…

Computation and Language · Computer Science 2026-03-24 Yuran Li , Di Wu , Benoit Boulet

Large reasoning models (LRMs) have demonstrated impressive capabilities in domains like mathematics and program synthesis. Despite their strong performance, LRMs often exhibit overthinking -- excessive and redundant reasoning steps that…

Machine Learning · Computer Science 2025-07-09 Haoxi Li , Sikai Bai , Jie Zhang , Song Guo

Simulation-based design space exploration (DSE) aims to efficiently optimize high-dimensional structured designs under complex constraints and expensive evaluation costs. Existing approaches, including heuristic and multi-step reinforcement…

Machine Learning · Computer Science 2025-06-05 Yifeng Xiao , Yurong Xu , Ning Yan , Masood Mortazavi , Pierluigi Nuzzo

Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs. Existing approaches synthesize shorter reasoning responses for LRMs…

Computation and Language · Computer Science 2026-03-02 Hexuan Deng , Wenxiang Jiao , Xuebo Liu , Jun Rao , Min Zhang

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

Computation and Language · Computer Science 2026-05-29 Ziqiang Cui , Yunpeng Weng , Xing Tang , Peiyang Liu , Shiwei Li , Bowei He , Jiamin Chen , Yansen Zhang , Xiuqiang He , Chen Ma

Large reasoning models (LRMs) like OpenAI-o1 have shown impressive capabilities in natural language reasoning. However, these models frequently demonstrate inefficiencies or inaccuracies when tackling complex mathematical operations. While…

Computation and Language · Computer Science 2025-10-24 Chengpeng Li , Zhengyang Tang , Ziniu Li , Mingfeng Xue , Keqin Bao , Tian Ding , Ruoyu Sun , Benyou Wang , Xiang Wang , Junyang Lin , Dayiheng Liu

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

Artificial Intelligence · Computer Science 2025-12-23 Qinglin Zeng , Jing Yang , Keze Wang

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…

Machine Learning · Computer Science 2026-02-16 Qinhang Wu , Sen Lin , Ming Zhang , Yingbin Liang , Ness B. Shroff

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Real-world wireless data are expensive to collect and often lack sufficient expert demonstrations, causing existing offline RL methods to overfit suboptimal behaviors and exhibit unstable performance. To address this issue, we propose CORE,…

Networking and Internet Architecture · Computer Science 2025-12-23 Lipeng Zu , Hansong Zhou , Yu Qian , Shayok Chakraborty , Yukun Yuan , Linke Guo , Xiaonan Zhang

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. These critical steps are challenging to identify with traditional reinforcement learning (RL) methods…

Machine Learning · Computer Science 2023-10-31 Chen Sun , Wannan Yang , Thomas Jiralerspong , Dane Malenfant , Benjamin Alsbury-Nealy , Yoshua Bengio , Blake Richards

The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexical similarity. The contrastive learning paradigm is…

Information Retrieval · Computer Science 2026-03-19 Guangzhi Wang , Yinghao Jiao , Zhi Liu
‹ Prev 1 2 3 10 Next ›