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。

2025-08-12 至 2025-08-12 共收录 93 信号源:cs.CL, cs.AI, cs.LG

1. 数学推理 4 篇

2502.04362 2025-08-12 cs.CL cs.AI 62%

LLMs can be easily Confused by Instructional Distractions

Yerin Hwang, Yongil Kim, Jahyun Koo, Taegwan Kang, Hyunkyung Bae, Kyomin Jung

机构 * IPAI, Seoul National University(IPAI,首尔国立大学) LG AI Research(LG人工智能研究所) Dept. of ECE, Seoul National University(电子工程系,首尔国立大学) SNU-LG AI Research Center(SNU-LG人工智能研究所)

专题命中 数学推理 :reasoning(abstract);分类 cs.CL、cs.AI

Comments 8 pages

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19483-19496, Vienna, Austria, July 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.08053 2025-08-12 cs.AI 57%

AdaptFlow: Adaptive Workflow Optimization via Meta-Learning

Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

机构 * Peking University(北京大学) University of Chinese Academy of Sciences(中国科学院大学) Microsoft(微软公司) Shanghai Jiaotong University(上海交通大学)

专题命中 数学推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07805 2025-08-12 cs.CL 57%

Can You Trick the Grader? Adversarial Persuasion of LLM Judges

Yerin Hwang, Dongryeol Lee, Taegwan Kang, Yongil Kim, Kyomin Jung

专题命中 数学推理 :reasoning(abstract);分类 cs.CL

Comments 19 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.24006 2025-08-12 cs.CL math.HO 57%

Large Language Models Don't Make Sense of Word Problems. A Scoping Review from a Mathematics Education Perspective

Anselm R. Strohmaier, Wim Van Dooren, Kathrin Seßler, Brian Greer, Lieven Verschaffel

专题命中 数学推理 :reasoning(abstract);分类 cs.CL

Comments v2: added analyses for GPT-5, also leading to small adjustments in the text, no major new interpretations

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 代码与定理证明 1 篇

2508.08171 2025-08-12 cs.SE cs.AI 57%

PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C

Pedro Orvalho, Marta Kwiatkowska

专题命中 代码与定理证明 :reasoning(abstract);分类 cs.AI

Comments 14 pages, 6 tables, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 逻辑推理 10 篇

2504.16832 2025-08-12 cs.CL 89%

GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning

Luu Quy Tung, Hoang Quoc Viet, Pham Bao Loc, Vo Trong Thu

机构 * John Von Neumann Institute(约翰·冯·诺依曼研究所)

专题命中 逻辑推理 :reasoning(title,abstract);logical reasoning(title);chain-of-thought(abstract);CoT(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07626 2025-08-12 cs.CV cs.RO 88%

AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning

Dejie Yang, Zijing Zhao, Yang Liu

机构 * Wangxuan Institute of Computer Technology, Peking University(北京大学计算机技术研究院) State Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室)

专题命中 逻辑推理 :reasoning(title,abstract);logical reasoning(title,abstract)

Comments Accepted by ICCV2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00160 2025-08-12 cs.CL cs.AI cs.LG 67%

Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework

Qihui Fan, Wenbo Li, Enfu Nan, Yixiao Chen, Lei Lu, Pu Zhao, Yanzhi Wang

机构 * Northeastern University(东北大学)

专题命中 逻辑推理 :reasoning(abstract);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.03788 2025-08-12 cs.HC 67%

Frontend Diffusion: Empowering Self-Representation of Junior Researchers and Designers Through Multi-agent System

Zijian Ding, Qinshi Zhang, Mohan Chi, Ziyi Wang

专题命中 逻辑推理 :reasoning(abstract);logical reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07163 2025-08-12 cs.RO cs.AI cs.NE 57%

Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Survey

Kamal Acharya, Iman Sharifi, Mehul Lad, Liang Sun, Houbing Song

机构 * Department of Information Systems, University of Maryland, Baltimore County(信息系统系,马里兰大学巴尔的摩分校) Department of Mechanical and Aerospace Engineering, The George Washington University(机械与航空航天工程系,乔治华盛顿大学) Department of Mechanical Engineering, Baylor University(机械工程系,贝勒大学)

专题命中 逻辑推理 :reasoning(abstract);分类 cs.AI

Comments 9 pages, 4 figures, IJCAI-2025 (accepted)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21839 2025-08-12 cs.CV cs.CL 57%

GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles

Mengyi Shan, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz

机构 * University of Washington(华盛顿大学)

专题命中 逻辑推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07935 2025-08-12 cs.SE 50%

SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows

Jingwen Zhou, Jieshan Chen, Qinghua Lu, Dehai Zhao, Liming Zhu

专题命中 逻辑推理 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.14594 2025-08-12 cs.CV 50%

Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems

Qihao Yuan, Kailai Li, Jiaming Zhang

机构 * Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen(格罗宁根大学伯努利学院) Computer Vision for Human-Computer Interaction Lab (cv:hci), Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院人机交互计算机视觉实验室)

专题命中 逻辑推理 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06722 2025-08-12 cs.RO 50%

Improved Obstacle Avoidance for Autonomous Robots with ORCA-FLC

Justin London

机构 * Dept. of Electrical Engineering and Computer Science(电气工程与计算机科学系) University of North Dakota(北达科他大学)

专题命中 逻辑推理 :planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06554 2025-08-12 cs.RO 50%

AquaChat++: LLM-Assisted Multi-ROV Inspection for Aquaculture Net Pens with Integrated Battery Management and Thruster Fault Tolerance

Abdelhaleem Saad, Waseem Akram, Irfan Hussain

机构 * Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, United Arab Emirates(卡利法大学自主机器人系统中心(KUCARS)、卡利法大学、阿拉伯联合酋长国)

专题命中 逻辑推理 :planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 规划推理 19 篇

2410.07096 2025-08-12 cs.AI 79%

Rejecting Hallucinated State Targets during Planning

Mingde Zhao, Tristan Sylvain, Romain Laroche, Doina Precup, Yoshua Bengio

机构 * McGill University(麦吉尔大学) Mila (Quebec AI Institute)(蒙特利尔AI研究所) Google Deepmind(谷歌DeepMind)

专题命中 规划推理 :planning(title,abstract);分类 cs.AI

Comments [20250810]: ICML 2025 Camera Ready, https://github.com/mila-iqia/delusions

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.16858 2025-08-12 cs.CL 79%

Planning with Diffusion Models for Target-Oriented Dialogue Systems

Hanwen Du, Bo Peng, Xia Ning

机构 * Department of Computer Science and Engineering, The Ohio State University, USA(计算机科学与工程系,俄亥俄州立大学) Department of Biomedical Informatics, The Ohio State University, USA(生物医学信息学系,俄亥俄州立大学) Translational Data Analytics Institute, The Ohio State University, USA(转化数据分析研究所,俄亥俄州立大学)

专题命中 规划推理 :planning(title,abstract);分类 cs.CL

Comments Accepted to ACL 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06891 2025-08-12 eess.IV cs.CV 78%

Fusion-Based Brain Tumor Classification Using Deep Learning and Explainable AI, and Rule-Based Reasoning

Melika Filvantorkaman, Mohsen Piri, Maral Filvan Torkaman, Ashkan Zabihi, Hamidreza Moradi

专题命中 规划推理 :reasoning(title);planning(abstract)

Comments 37 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07186 2025-08-12 cs.AI cs.MA 74%

Multi-Dimensional Summarization Agents with Context-Aware Reasoning over Enterprise Tables

Amit Dhanda

机构 * Amazon(亚马逊)

专题命中 规划推理 :reasoning(title);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01680 2025-08-12 cs.LG cs.AI 73%

Neurosymbolic AI for Travel Demand Prediction: Integrating Decision Tree Rules into Neural Networks

Kamal Acharya, Mehul Lad, Liang Sun, Houbing Song

机构 * Department of Information Systems University of Maryland Baltimore County Baltimore, MD, US(信息系统系马里兰大学巴尔的摩县) Department of Mechanical Engineering Baylor University Waco,TX, US(机械工程系贝勒大学)

专题命中 规划推理 :reasoning(abstract);planning(abstract);分类 cs.AI、cs.LG

Comments 9 pages, 5 figures, this paper is under review in the conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.08240 2025-08-12 cs.RO cs.CV 67%

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen

专题命中 规划推理 :reasoning(abstract);planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07308 2025-08-12 cs.CL cs.AI cs.IR cs.LG 67%

HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways

Cristian Cosentino, Annamaria Defilippo, Marco Dossena, Christopher Irwin, Sara Joubbi, Pietro Liò

专题命中 规划推理 :reasoning(abstract);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.08088 2025-08-12 cs.IR cs.AI cs.CL 62%

HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

Jiejun Tan, Zhicheng Dou, Yan Yu, Jiehan Cheng, Qiang Ju, Jian Xie, Ji-Rong Wen

机构 * Baichuan(百川)

专题命中 规划推理 :reasoning(abstract);分类 cs.CL、cs.AI

Comments Code and datasets are available at https://github.com/plageon/HierSearch

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08049 2025-08-12 stat.ML cs.AI cs.LG 62%

Physics-Informed Teleconnection-Aware Transformer for Global Subseasonal-to-Seasonal Forecasting

Tengfei Lyu, Weijia Zhang, Hao Liu

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) The Hong Kong University of Science and Technology(香港科技大学)

专题命中 规划推理 :planning(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.12997 2025-08-12 cs.LG cs.AI 62%

Ehrenfeucht-Haussler Rank and Chain of Thought

Pablo Barceló, Alexander Kozachinskiy, Tomasz Steifer

机构 * National Center for Artificial Intelligence (CENIA Chile)(国家人工智能中心(智利CENIA)) Millennium Institute for Foundational Research on Data (IMFD Chile)(数据基础研究千年研究所(智利IMFD)) Institute for Mathematical and Computational Engineering, Pontifical Catholic University of Chile(数学与计算工程研究所,智利天主教大学) Institute of Fundamental Technological Research, Polish Academy of Sciences(基础技术研究所,波兰科学院)

专题命中 规划推理 :CoT(abstract);分类 cs.AI、cs.LG

Comments Changes to the previous version: new results about PAC learning for functions of bounded multi-head rank are addes

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06497 2025-08-12 q-fin.CP cs.AI cs.LG 62%

Forecasting Commodity Price Shocks Using Temporal and Semantic Fusion of Prices Signals and Agentic Generative AI Extracted Economic News

Mohammed-Khalil Ghali, Cecil Pang, Oscar Molina, Carlos Gershenson-Garcia, Daehan Won

专题命中 规划推理 :planning(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15322 2025-08-12 cs.LG cs.AI 62%

UoMo: A Universal Model of Mobile Traffic Forecasting for Wireless Network Optimization

Haoye Chai, Shiyuan Zhang, Xiaoqian Qi, Baohua Qiu, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University(电子工程系,BNRist,清华大学)

专题命中 规划推理 :planning(abstract);分类 cs.AI、cs.LG

Comments 2025 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07507 2025-08-12 cs.CY cs.AI 57%

Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research

Rashid Mushkani

专题命中 规划推理 :planning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07466 2025-08-12 cs.AI 57%

Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs

Dom Huh, Prasant Mohapatra

机构 * UC Davis(加州大学戴维斯分校) University of South Florida(佛罗里达州立大学)

专题命中 规划推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06980 2025-08-12 cs.AI 57%

Simulating Biological Intelligence: Active Inference with Experiment-Informed Generative Model

Aswin Paul, Moein Khajehnejad, Forough Habibollahi, Brett J. Kagan, Adeel Razi

机构 * Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Clayton 3800, Australia(墨尔本大学心理科学学院脑与心理健康研究所) VERSES, Los Angeles, California, USA(VERSES,美国洛杉矶,加利福尼亚州) Cortical Labs Pty Ltd, Melbourne 3056, Australia(Cortical Labs Pty Ltd,澳大利亚墨尔本3056) CIFAR Azrieli Global Scholars Program, CIFAR, Toronto, Canada(CIFAR阿兹里埃利全球学者计划,加拿大多伦多)

专题命中 规划推理 :planning(abstract);分类 cs.AI

Comments 18 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏