arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

共收录 5878 信号源:cs.CL, cs.AI, cs.LG

1. 其他推理 5878 篇

2510.11502 2025-10-14 cs.LG 57%

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors

Alexis Ross, Jacob Andreas

机构 * MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11143 2025-10-14 cs.AI cs.HC 57%

Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis

Chuke Chen, Biao Luo, Nan Li, Boxiang Wang, Hang Yang, Jing Guo, Ming Xu

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

Comments 19 pages,5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09815 2025-10-14 cs.CV cs.AI 57%

Towards Understanding Ambiguity Resolution in Multimodal Inference of Meaning

Yufei Wang, Adriana Kovashka, Loretta Fernández, Marc N. Coutanche, Seth Wiener

机构 * University of Pittsburgh(匹兹堡大学) Carnegie Mellon University(卡内基梅隆大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

Comments Accepted to International Conference on Development and Learning (ICDL) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10736 2025-10-14 cs.CL 57%

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs

Xiangqi Jin, Yuxuan Wang, Yifeng Gao, Zichen Wen, Biqing Qi, Dongrui Liu, Linfeng Zhang

专题命中 其他推理 :chain-of-thought(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.19029 2025-10-13 cs.LG 57%

Revisiting associative recall in modern recurrent models

Destiny Okpekpe, Antonio Orvieto

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) ELLIS Institute(ELLIS研究所) Tübingen AI Center(图宾根人工智能中心)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08981 2025-10-13 cs.SE cs.AI 57%

SEER: Sustainability Enhanced Engineering of Software Requirements

Mandira Roy, Novarun Deb, Nabendu Chaki, Agostino Cortesi

机构 * Ca' Foscari University(卡沃斯卡里大学) University of Calgary(卡尔加里大学) University of Calcutta(加尔各答大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

Comments Main Paper: 32 pages, References: 3 pages, Appendix: 13 pages. Submitted to the Journal of Systems and Software, Elsevier

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08389 2025-10-10 cs.AI 57%

Revisiting Hallucination Detection with Effective Rank-based Uncertainty

Rui Wang, Zeming Wei, Guanzhang Yue, Meng Sun

机构 * Peking University(北京大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06825 2025-10-10 cs.CL 57%

Adaptive Tool Generation with Models as Tools and Reinforcement Learning

Chenpeng Wang, Xiaojie Cheng, Chunye Wang, Linfeng Yang, Lei Zhang

机构 * Chenpeng Wang(王晨鹏) Xiaojie Cheng(程晓杰) Chunye Wang(王春业) Linfeng Yang(杨林峰) Lei Zhang(张磊)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06954 2025-10-09 cs.LG 57%

From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

Zheng-An Chen, Tao Luo

机构 * School of Mathematical Sciences, Shanghai Jiao Tong University(上海交通大学数学科学学院) Institute of Natural Sciences, MOE-LSC, CMA-Shanghai, Shanghai Jiao Tong University(上海交通大学自然科学院)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06750 2025-10-09 cs.CL 57%

Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs

Jaeseong Lee, Dayoung Kwon, seung-won hwang

机构 * Computer Science and Engineering, Seoul National University(计算机科学与工程,首尔国立大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23580 2025-10-09 cs.CL 57%

LLM Hallucination Detection: HSAD

JinXin Li, Gang Tu, JunJie Hu

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

Comments in Chinese language

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05133 2025-10-08 cs.CL 57%

Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios

Y. Du, G. Wu, G. Tang, W. Wang, Q. Fan

机构 * Independent Research Collaboration(独立研究者)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

Comments 17 pages. Technical report

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04710 2025-10-07 cs.LG 57%

ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts

Zexin Wang, Changhua Pei, Yang Liu, Hengyue Jiang, Quan Zhou, Haotian Si, Hang Cui, Jianhui Li, Gaogang Xie, Jingjing Li, Dan Pei

机构 * Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心) Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州先进研究所) Tsinghua University(清华大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

Comments 13 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04615 2025-10-07 eess.SY cs.AI cs.SY 57%

Design Process of a Self Adaptive Smart Serious Games Ecosystem

X. Tao, P. Chen, M. Tsami, F. Khayati, M. Eckert

机构 * Research Center on Software Technologies and Multimedia Systems for Sustainability (CITSEM), Universidad Politécnica de Madrid (UPM), Spain(软件技术与多媒体系统可持续性研究所以及马德里理工大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03612 2025-10-07 cs.AI cs.CR 57%

Cross-Modal Content Optimization for Steering Web Agent Preferences

Tanqiu Jiang, Min Bai, Nikolaos Pappas, Yanjun Qi, Sandesh Swamy

机构 * Stony Brook University(石溪大学) AWS AI Labs(亚马逊人工智能实验室)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17601 2025-10-07 cs.CL 57%

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs

Jiawei Kong, Hao Fang, Xiaochen Yang, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Ke Xu, Han Qiu

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学) Department of Software Engineering, Harbin Institute of Technology(哈尔滨工业大学软件工程系) School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学深圳校区计算机科学与技术学院) Institute for Network Sciences and Cyberspace, Tsinghua University(清华大学网络科学与空间研究院)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.20140 2025-10-07 cs.AI 57%

MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection

Kumud Lakara, Georgia Channing, Christian Rupprecht, Juil Sock, Philip Torr, John Collomosse, Christian Schroeder de Witt

机构 * University of Oxford, Oxford, UK(牛津大学) BBC AI Research, London, UK(BBC人工智能研究) University of Surrey, Guildford, UK(萨里大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03286 2025-10-07 q-bio.NC cs.AI 57%

A Biologically Interpretable Cognitive Architecture for Online Structuring of Episodic Memories into Cognitive Maps

E. A. Dzhivelikian, A. I. Panov

机构 * Cognitive AI Lab(认知人工智能实验室)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03204 2025-10-06 cs.CL 57%

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Léo Boisvert, Massimo Caccia, Jérémy Espinas, Alexandre Aussem, Véronique Eglin, Alexandre Lacoste

机构 * LIRIS - CNRS, INSA Lyon, Universite Claude Bernard Lyon 1(LIRIS - CNRS,INSA里昂,克劳德·贝尔纳大学里昂) Esker ServiceNow Research(ServiceNow研究) Mila - Quebec AI Institute(魁北克人工智能研究所) McGill University(麦吉尔大学) Polytechnique Montréal(蒙特利尔理工学院)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02752 2025-10-06 cs.CL 57%

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback

Hangfan Zhang, Siyuan Xu, Zhimeng Guo, Huaisheng Zhu, Shicheng Liu, Xinrun Wang, Qiaosheng Zhang, Yang Chen, Peng Ye, Lei Bai, Shuyue Hu

机构 * Pennsylvania State University(宾夕法尼亚州立大学) Singapore Management University(新加坡管理大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21117 2025-10-06 cs.IR cs.AI 57%

A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges

Rahul Raja, Anshaj Vats, Arpita Vats, Anirban Majumder

机构 * Linkedin, Carnegie Mellon University, Stanford University(LinkedIn、卡内基梅隆大学、斯坦福大学) Meta Linkedin, Meta AI, Amazon, Boston University(LinkedIn、Meta AI、亚马逊、波士顿大学) Amazon(亚马逊)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.04404 2025-10-06 cs.AI 57%

LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers

Jingze Zhu, Yongliang Wu, Wenbo Zhu, Jiawang Cao, Yanqiang Zheng, Jiawei Chen, Xu Yang, Bernt Schiele, Jonas Fischer, Xinting Hu

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

Comments The submission was made before undergoing the required review by the co-authors' affiliated institutions. We are withdrawing the paper to allow for the completion of the institutional review process

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01664 2025-10-03 cs.AI 57%

GuruAgents: Emulating Wise Investors with Prompt-Guided LLM Agents

Yejin Kim, Youngbin Lee, Juhyeong Kim, Yongjae Lee

机构 * AI Quant Lab, MODULABS(AI量化实验室,MODULABS) Ulsan National Institute of Science and Technology(乌山国立科学与技术研究所)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

Comments 7 Pages, 2 figures

Journal ref CIKM 2025 Workshop on Advances in Financial AI: Innovations, Risk, and Responsibility in the Era of LLMs

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01248 2025-10-03 cs.CL 57%

SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs

Ruyue Liu, Rong Yin, Xiangzhen Bo, Xiaoshuai Hao, Yong Liu, Jinwen Zhong, Can Ma, Weiping Wang

机构 * Institute of Information Engineering, CAS(信息工程研究所,中国科学院) School of Cyberspace Security, UCAS(网络安全学院,中国科学院大学) Wuhan University of Technology(武汉理工大学) Xiaomi EV(小米汽车) Renmin University of China(中国人民大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01234 2025-10-03 cs.CL 57%

LLMRank: Understanding LLM Strengths for Model Routing

Shubham Agrawal, Prasang Gupta

机构 * Zeno AI

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

Comments 13 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13449 2025-10-03 cs.LG physics.chem-ph 57%

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model

Dongki Kim, Wonbin Lee, Sung Ju Hwang

机构 * KAIST(韩国科学技术院)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.00909 2025-10-02 cs.HC cs.AI 57%

"We are not Future-ready": Understanding AI Privacy Risks and Existing Mitigation Strategies from the Perspective of AI Developers in Europe

Alexandra Klymenko, Stephen Meisenbacher, Patrick Gage Kelley, Sai Teja Peddinti, Kurt Thomas, Florian Matthes

机构 * Technical University of Munich(慕尼黑技术大学) Google(谷歌)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

Comments 20 pages, 1 figure, 4 tables. Accepted to SOUPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10458 2025-10-02 cs.CV cs.CL cs.HC 57%

GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Run Luo, Lu Wang, Wanwei He, Longze Chen, Jiaming Li, Xiaobo Xia

机构 * Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究所) University of Chinese Academy of Sciences(中国科学院大学) National University of Singapore(新加坡国立大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.19778 2025-10-02 cs.AI 57%

Multimodal Large Language Models for Bioimage Analysis

Shanghang Zhang, Gaole Dai, Tiejun Huang, Jianxu Chen

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26114 2025-10-01 cs.LG 57%

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

Jaesung R. Park, Junsu Kim, Gyeongman Kim, Jinyoung Jo, Sean Choi, Jaewoong Cho, Ernest K. Ryu

机构 * Department of Mathematics, UCLA(UCLA数学系) Department of Mathematical Sciences, Seoul National University(首尔国立大学数学科学系) KRAFTON Department of Linguistics, Stanford University(斯坦福大学语言学系) Department of Computer Science and Engineering, Santa Clara University(圣克拉拉大学计算机科学与工程系)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏