大模型推理能力 - arXivDaily 专题

2510.23648 2025-10-29 cs.SI cs.AI 57%

RoGBot: Relationship-Oblivious Graph-based Neural Network with Contextual Knowledge for Bot Detection

Ashutosh Anshul, Mohammad Zia Ur Rehman, Sri Akash Kadali, Nagendra Kumar

机构 * Indian Institute of Technology Indore（印度理工学院印多尔分校）； University of Maryland, College Park, USA（美国马里兰大学学院公园分校）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments Submitted to IEEE

2503.02103 2025-10-28 cs.CL 57%

Superficial Self-Improved Reasoners Benefit from Model Merging

Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Leyan Pan, Soroush Vosoughi, Wenke Lee

机构 * Georgia Institute of Technology（佐治亚理工学院）； Dartmouth College（达特茅斯学院）； University of Notre Dame（诺丁汉大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments EMNLP 2025

2507.17394 2025-10-28 cs.CV cs.AI 57%

HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs

Zhaolin Cai, Fan Li, Ziwei Zheng, Yanjun Qin

机构 * Xinjiang University（新疆大学）； Xi'an Jiaotong University（西安交通大学）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments Accepted by ACM MM 2025

2510.22070 2025-10-28 cs.LG cs.CV eess.IV stat.ML 57%

MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification

Luca Caldera, Giacomo Bottacini, Lara Cavinato

机构 * MOX, Department of Mathematics Politecnico di Milano（米兰理工大学数学系MOX部门）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

2510.21323 2025-10-27 cs.CV cs.LG 57%

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Shufan Shen, Junshu Sun, Qingming Huang, Shuhui Wang

机构 * Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS（智能信息处理重点实验室，计算技术研究所，中国科学院）； University of Chinese Academy of Sciences（中国科学院大学）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments Accepted by NeurIPS 2025

2505.09396 2025-10-27 cs.AI cs.MA 57%

The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners

Vince Trencsenyi, Agnieszka Mensfelt, Kostas Stathis

机构 * Department of Computer Science, Royal Holloway University of London（皇家霍洛威大学计算机科学系）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

2510.20369 2025-10-24 cs.LG 57%

Ask a Strong LLM Judge when Your Reward Model is Uncertain

Zhenghao Xu, Qin Lu, Qingru Zhang, Liang Qiu, Ilgee Hong, Changlong Yu, Wenlin Yao, Yao Liu, Haoming Jiang, Lihong Li, Hyokun Yun, Tuo Zhao

机构 * Georgia Institute of Technology（佐治亚理工学院）； Amazon（亚马逊）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments NeurIPS 2025, 18 pages

2508.17536 2025-10-24 cs.CL cs.MA 57%

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li

机构 * Department of Computer Sciences, University of Wisconsin-Madison（计算机科学系，威斯康星大学麦迪逊分校）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments NeurIPS 2025 Spotlight

2503.19878 2025-10-23 cs.CL cs.IR 57%

CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation

Nengbo Wang, Xiaotian Han, Jagdip Singh, Jing Ma, Vipin Chaudhary

机构 * Department of Computer and Data Sciences, Case Western Reserve University（计算机与数据科学系，凯斯西储大学）； Department of Design and Innovation, Case Western Reserve University（设计与创新系，凯斯西储大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments Accepted at Findings of ACL 2025

2510.16933 2025-10-21 cs.DC cs.AI 57%

Tutoring LLM into a Better CUDA Optimizer

Matyáš Brabec, Jiří Klepl, Michal Töpfer, Martin Kruliš

机构 * Charles University（查理大学）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in Euro-Par 2025: Parallel Processing, Part II, and is available online at https://doi.org/10.1007/978-3-031-99857-7_18

Journal ref Euro-Par 2025: Parallel Processing. Euro-Par 2025. Lecture Notes in Computer Science, vol 15901. Springer, Cham

2510.16885 2025-10-21 cs.LG 57%

UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains

Duo Wang, Yuan Zuo, Guangyue Lu, Junjie Wu

机构 * MIIT Key Laboratory of Data Intelligence and Management, Beihang University（信息科技部数据智能与管理重点实验室，北京航空航天大学）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Journal ref NeurIPS 2025

2506.04650 2025-10-21 cs.LG 57%

Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction

Zesheng Ye, Chengyi Cai, Ruijiang Dong, Jianzhong Qi, Lei Feng, Pin-Yu Chen, Feng Liu

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

2510.16290 2025-10-21 cs.CV cs.CL 57%

Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models

Yue Zheng, Xiufang Shi, Jiming Chen, Yuanchao Shu

机构 * Zhejiang University of Technology（浙江工业大学）； Zhejiang University（浙江大学）； Hangzhou Dianzi University（杭州电子科技大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2510.16080 2025-10-21 q-bio.QM cs.AI 57%

TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

Kerem Delikoyun, Qianyu Chen, Win Sen Kuan, John Tshon Yit Soong, Matthew Edward Cove, Oliver Hayden

机构 * Technical University of Munich（慕尼黑技术大学）； National University of Singapore（新加坡国立大学）； National University Hospital（新加坡国立大学医院）

专题命中其他推理：CoT(abstract)；分类 cs.AI

2510.15917 2025-10-21 cs.AR cs.AI cs.DC 57%

Intent-Driven Storage Systems: From Low-Level Tuning to High-Level Understanding

Shai Bergman, Won Wook Song, Lukas Cavigelli, Konstantin Berestizshevsky, Ke Zhou, Ji Zhang

机构 * Huawei Zurich Research Center（华为苏黎世研究中心）； Huazhong University of Science and Technology（华中科技大学）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

2510.15706 2025-10-20 cs.IR cs.CL 57%

GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery

Italo Luis da Silva, Hanqi Yan, Lin Gui, Yulan He

机构 * Department of Informatics（信息学系）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments 9 pages, 6 figures, 3 tables, EMNLP 2025 Demo paper

2510.15317 2025-10-20 cs.AI 57%

VERITAS: Leveraging Vision Priors and Expert Fusion to Improve Multimodal Data

Tingqiao Xu, Ziru Zeng, Jiayu Chen

机构 * Shanghai Jiao Tong University（上海交通大学）； Fudan University（复旦大学）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments Accepted to EMNLP 2025 (Main Conference)

2505.07176 2025-10-20 cs.MA cs.AI 57%

Internet of Agents: Fundamentals, Applications, and Challenges

Yuntao Wang, Shaolong Guo, Yanghe Pan, Zhou Su, Fahao Chen, Tom H. Luan, Peng Li, Jiawen Kang, Dusit Niyato

机构 * School of Cyber Science and Engineering, Xi'an Jiaotong University（网络安全科学与工程学院，西安交通大学）； School of Artificial Intelligence, Shandong University（人工智能学院，山东大学）； School of Automation, Guangdong University of Technology（自动化学院，广东技术大学）； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments 25 pages,10 figures, 10 tables. Accepted by IEEE TCCN in Oct. 2025

2502.15176 2025-10-20 cs.CV cs.AI 57%

Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review

Arpan Mahara, Naphtali Rishe

机构 * Knight Foundation School of Computing and Information Sciences, Florida International University（骑士基金会计算与信息科学学院，佛罗里达国际大学）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments 34 pages, 4 Figures, 10 Tables

2510.14455 2025-10-17 cs.LG q-bio.BM 57%

Coder as Editor: Code-driven Interpretable Molecular Optimization

Wenyu Zhu, Chengzhu Li, Xiaohe Tian, Yifan Wang, Yinjun Jia, Jianhui Wang, Bowen Gao, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan

机构 * Institute for AI Industry Research, Tsinghua University（人工智能产业研究院，清华大学）； Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）； School of Pharmaceutical Sciences, Peking University（北京大学药学院）； University of Electronic Science and Technology of China（电子科技大学）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

2510.13902 2025-10-17 cs.CL cs.CY 57%

Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory

Nicole Smith-Vaniz, Harper Lyon, Lorraine Steigner, Ben Armstrong, Nicholas Mattei

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2510.13825 2025-10-17 cs.CR cs.AI 57%

A2AS: Agentic AI Runtime Security and Self-Defense

Eugene Neelou, Ivan Novikov, Max Moroz, Om Narayan, Tiffany Saade, Mika Ayenson, Ilya Kabanov, Jen Ozmen, Edward Lee, Vineeth Sai Narajala, Emmanuel Guilherme Junior, Ken Huang, Huseyin Gulsin, Jason Ross, Marat Vyshegorodtsev, Adelin Travers, Idan Habler, Rahul Jadav

专题命中其他推理：reasoning(abstract)；分类 cs.AI

2510.13668 2025-10-16 cs.DC cs.LG 57%

Adaptive Rescheduling in Prefill-Decode Disaggregated LLM Inference

Zhibin Wang, Zetao Hong, Xue Li, Zibo Wang, Shipeng Li, Qingkai Meng, Qing Wang, Chengying Huan, Rong Gu, Sheng Zhong, Chen Tian

机构 * State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）； Nanjing University（南京大学）； Alibaba Group（阿里巴巴集团）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

2510.13190 2025-10-16 cs.CL 57%

SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs

Juan Ren, Mark Dras, Usman Naseem

机构 * School of Computing, Macquarie University（计算机学院，麦考瑞大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments Preprint

2510.11052 2025-10-16 cs.CL 57%

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

Qinglin Zhu, Yizhen Yao, Runcong Zhao, Yanzheng Xiang, Amrutha Saseendran, Chen Jin, Philip Teare, Bin Liang, Yulan He, Lin Gui

机构 * King’s College London（伦敦国王学院）； The Alan Turing Institute（艾伦·图灵研究所）； Centre for AI, Data Science & Artificial Intelligence, BioPharmaceuticals R&D, AstraZeneca（人工智能、数据科学与人工智能研究中心，生物制药研发，阿斯利康）； The Chinese University of Hong Kong（香港中文大学）； MoE Lab, CUHK（CUHK MoE实验室）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2510.12697 2025-10-15 cs.AI 57%

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

Tianyu Hu, Zhen Tan, Song Wang, Huaizhi Qu, Tianlong Chen

机构 * Arizona State University（亚利桑那州立大学）； University of Central Florida（中央佛罗里达大学）； UNC Chapel Hill（北卡罗来纳大学教堂山分校）

专题命中其他推理：reasoning(abstract)；分类 cs.AI

2510.12185 2025-10-15 cs.CL cs.SD 57%

Not in Sync: Unveiling Temporal Bias in Audio Chat Models

Jiayu Yao, Shenghua Liu, Yiwei Wang, Rundong Cheng, Lingrui Mei, Baolong Bi, Zhen Xiong, Xueqi Cheng

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； University of California, Merced（加州大学默塞德分校）； Beijing University of Posts and Telecommunications（北京邮电大学）； University of Southern California（南加州大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2510.11584 2025-10-15 cs.CL cs.CR 57%

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings

Ting Li, Yang Yang, Yipeng Yu, Liang Yao, Guoqing Chao, Ruifeng Xu

机构 * Sun Yat-sen University（中山大学）； Alibaba Inc.（阿里巴巴公司）； Harbin Institute of Technology（哈尔滨工业大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments 13 pages

2505.18943 2025-10-15 cs.CL 57%

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Xuanming Zhang, Yuxuan Chen, Samuel Yeh, Sharon Li

机构 * Tsinghua University（清华大学）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments NeurIPS 2025 Spotlight

2502.04075 2025-10-15 cs.CL 57%

From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models

Yurui Dong, Luozhijie Jin, Yao Yang, Bingjie Lu, Jiaxi Yang, Zhi Liu

机构 * State Key Laboratory on Technologies for Chinese Medicine Pharmaceutical Process Control and Intelligent Manufacture（中药制药过程控制与智能制造技术国家重点实验室）； Zhejiang Lab（浙江实验室）

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments 43 pages, 5 figures

1. 其他推理 5878 篇

RoGBot: Relationship-Oblivious Graph-based Neural Network with Contextual Knowledge for Bot Detection

Superficial Self-Improved Reasoners Benefit from Model Merging

HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs

MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners

Ask a Strong LLM Judge when Your Reward Model is Uncertain

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation

Tutoring LLM into a Better CUDA Optimizer

UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains

Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction

Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models

TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

Intent-Driven Storage Systems: From Low-Level Tuning to High-Level Understanding

GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery

VERITAS: Leveraging Vision Priors and Expert Fusion to Improve Multimodal Data

Internet of Agents: Fundamentals, Applications, and Challenges

Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review

Coder as Editor: Code-driven Interpretable Molecular Optimization

Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory

A2AS: Agentic AI Runtime Security and Self-Defense

Adaptive Rescheduling in Prefill-Decode Disaggregated LLM Inference

SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

Not in Sync: Unveiling Temporal Bias in Audio Chat Models

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models