语言大模型 / LLM

2508.01169 2025-08-05 cs.CY 75%

WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

Chengzhang Zhu, Cecile H. Sam, Yanlai Wu, Ying Tang

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)

2508.02260 2025-08-05 cs.CL cs.AI 73%

Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning

Jia Deng, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Ji-Rong Wen

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 7 pages, 20 figures

2508.01773 2025-08-05 cs.AI cs.CL 73%

Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2506.21734 2025-08-05 cs.AI cs.LG 73%

Hierarchical Reasoning Model

Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, Yasin Abbasi Yadkori

机构 * Sapient Intelligence

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

2507.23735 2025-08-05 cs.RO cs.AI cs.MA 70%

Distributed AI Agents for Cognitive Underwater Robot Autonomy

Markus Buchholz, Ignacio Carlucho, Michele Grimaldi, Yvan R. Petillot

机构 * School of Engineering & Physical Sciences, Heriot-Watt University（工程与物理科学学院，赫里奥特-瓦特大学）

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.AI

2507.15822 2025-08-05 cs.SE cs.AI 70%

Do AI models help produce verified bug fixes?

Li Huang, Ilgiz Mustafin, Marco Piccioni, Alessandro Schena, Reto Weber, Bertrand Meyer

机构 * Constructor Institute of Technology（构造技术研究所）

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.AI

2508.02120 2025-08-05 cs.AI 70%

Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models

Linan Yue, Yichao Du, Yizhi Wang, Weibo Gao, Fangzhou Yao, Li Wang, Ye Liu, Ziyu Xu, Qi Liu, Shimin Di, Min-Ling Zhang

机构 * School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）； Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education（教育部计算机网络与信息集成重点实验室）； University of Science and Technology of China（中国科学技术大学）； Alibaba Group（阿里巴巴集团）

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.AI

2508.01134 2025-08-05 cs.LG 70%

Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice

Ran Li, Lingshu Zeng

机构 * Ran Li School of Information Science and Technology, Northeast Normal University, Changchun, China（Ran Li 信息科学与技术学院，东北师范大学，中国长春）

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 27 pages, 4 figures

2508.01715 2025-08-05 cs.RO 67%

Towards Zero-Shot Terrain Traversability Estimation: Challenges and Opportunities

Ida Germann, Mark O. Mints, Peer Neubert

机构 * Intelligent Autonomous Systems Group, Institute of Computational Visualisitics, University of Koblenz（智能自主系统组，计算可视化研究所，科隆大学）

专题命中推理与问题求解：language model(abstract)；foundation model(abstract)

Comments Accepted and presented at the 1st German Robotics Conference (GRC); March 13-15, 2025, Nuremberg, Germany https://ras.papercept.net/conferences/conferences/GRC25/program/GRC25_ContentListWeb_3.html#sada_48

2508.01338 2025-08-05 cs.CV cs.AI 57%

Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework

Ziqi Sheng, Junyan Wu, Wei Lu, Jiantao Zhou

专题命中推理与问题求解：language model(abstract)；分类 cs.AI

2507.12441 2025-08-05 cs.CV cs.LG 57%

Describe Anything Model for Visual Question Answering on Text-rich Images

Yen-Linh Vu, Dinh-Thang Duong, Truong-Binh Duong, Anh-Khoi Nguyen, Thanh-Huy Nguyen, Le Thien Phuc Nguyen, Jianhua Xing, Xingjian Li, Tianyang Wang, Ulas Bagci, Min Xu

机构 * AI VIETNAM Lab（AI越南实验室）； Carnegie Mellon University（卡内基梅隆大学）； University of Wisconsin - Madison（威斯康星大学麦迪逊分校）； University of Pittsburgh（匹兹堡大学）； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）； Northwestern University（西北大学）

专题命中推理与问题求解：language model(abstract)；分类 cs.LG

Comments 11 pages, 5 figures. Accepted to VisionDocs @ ICCV 2025

2504.10011 2025-08-05 cs.RO 50%

KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks

Edgar Anarossi, Yuhwan Kwon, Hirotaka Tahara, Shohei Tanaka, Keisuke Shirai, Masashi Hamaya, Cristian C. Beltran-Hernandez, Atsushi Hashimoto, Takamitsu Matsubara

机构 * Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology（信息科学系，科学技术研究生学校，科学技术研究所）； Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University（电气电子工程系，工学科学大学）； Department of Electronics, Kobe City College of Technology（电子系，神户市立技术学院）； OMRON SINIC X Corporation（OMRON SINIC X公司）

专题命中推理与问题求解：language model(abstract)

Comments Published in IEEE Access, Jul 14 2025

Journal ref IEEE Access, vol. 13, pp. 125420-125441, 2025

2503.19351 2025-08-05 cs.CV 50%

Multi-Object Sketch Animation by Scene Decomposition and Motion Planning

Jingyu Liu, Zijie Xin, Yuhan Fu, Ruixiang Zhao, Bangxiang Lan, Xirong Li

专题命中推理与问题求解：LLM(abstract)

Comments Accepted by ICCV 2025

2508.02429 2025-08-05 cs.AI cs.LG 92%

Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting

Miaosen Luo, Jiesen Long, Zequn Li, Yunying Yang, Yuncheng Jiang, Sijie Mai

机构 * School of Computer Science, South China Normal University（华南师范大学计算机科学学院）； School of Information Technology in Education, South China Normal University（华南师范大学教育信息技术学院）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；prompting(title,abstract)；分类 cs.AI、cs.LG

2508.02312 2025-08-05 cs.CR cs.AI 90%

A Survey on Data Security in Large Language Models

Kang Chen, Xiuze Zhou, Yuanguo Lin, Jinhe Su, Yuanhui Yu, Li Shen, Fan Lin

机构 * School of Computer Engineering, Jimei University, Xiamen, 361021, China（厦门大学计算机工程学院）； College of Science, Mathematics and Technology, Wenzhou-Kean University, Wenzhou, 325060, China（温州-凯恩大学科学、数学与技术学院）； The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China（香港科学与技术大学（广州））； School of Professional Studies, New York University, New York, 10003, United States（纽约大学专业研究学院）； School of Informatics, Xiamen University, Xiamen, 361102, China（厦门大学信息学院）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；RLHF(abstract)

2508.01708 2025-08-05 cs.CL 90%

Am I Blue or Is My Hobby Counting Teardrops? Expression Leakage in Large Language Models as a Symptom of Irrelevancy Disruption

Berkay Köprü, Mehrzad Mashal, Yigit Gurses, Akos Kadar, Maximilian Schmitt, Ditty Mathew, Felix Burkhardt, Florian Eyben, Björn W. Schuller

机构 * audEERING GmbH（audEERING公司）； Agile Robots SE（Agile Robots公司）； Chair of Health Informatics, Technical University of Munich（技术大学慕尼黑健康信息学系）； Group on Language, Audio & Music, Imperial College London（伦敦帝国学院语言、音频与音乐组）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

2507.18182 2025-08-05 cs.CL cs.AI 90%

SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models

Wonjun Jeong, Dongseok Kim, Taegkeun Whangbo

机构 * Department of Computer Engineering（计算机工程系）； Gachon University（高城大学）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments Comments: 34 pages, 1 figure. v2: All "Consequence." statements in the Theoretical Analysis section relabeled as "Corollary."; duplicated values in Table 20 (previously identical to Table 15) corrected

2508.02430 2025-08-05 cs.CL 89%

AI-Based Measurement of Innovation: Mapping Expert Insight into Large Language Model Applications

Robin Nowak, Patrick Figge, Carolin Haeussler

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2508.01514 2025-08-05 cs.IR cs.LG 89%

End-to-End Personalization: Unifying Recommender Systems with Large Language Models

Danial Ebrat, Tina Aminian, Sepideh Ahmadian, Luis Rueda

机构 * University of Windsor（温莎大学）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.LG

Comments Second Workshop on Generative AI for Recommender Systems and Personalization at the ACM Conference on Knowledge Discovery and Data Mining (GenAIRecP@KDD 2025)

2507.22952 2025-08-05 cs.HC cs.CV cs.LG 89%

Automated Label Placement on Maps via Large Language Models

Harry Shomer, Jiejun Xu

机构 * University of Texas at Arlington（德克萨斯理工大学）； HRL Laboratories（HRL实验室）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)；分类 cs.LG

Comments Workshop on AI for Data Editing (AI4DE) at KDD 2025

2507.10852 2025-08-05 cs.CL 89%

LLMs on Trial: Evaluating Judicial Fairness for Large Language Models

Yiran Hu, Zongyue Xue, Haitao Li, Siyuan Zheng, Qingjing Chen, Shaochun Wang, Xihan Zhang, Ning Zheng, Yun Liu, Qingyao Ai, Yiqun Liu, Charles L. A. Clarke, Weixing Shen

机构 * Tsinghua University, China（清华大学）； University of Waterloo, Canada（滑铁卢大学）； Yale Law School, USA（耶鲁法学院）； Shanghai Jiao Tong University, China（上海交通大学）； University of Bologna, Italy（博洛尼亚大学）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2501.12934 2025-08-05 cs.SE cs.LG 89%

Correctness Assessment of Code Generated by Large Language Models Using Internal Representations

Tuan-Dung Bui, Thanh Trong Vu, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

机构 * Faculty of Information Technology, VNU University of Engineering and Technology（信息科技学院，越南工程大学）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.LG

2406.12307 2025-08-05 cs.CL 89%

Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?

Seungbin Yang, ChaeHun Park, Taehee Kim, Jaegul Choo

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL

2508.01451 2025-08-05 cs.CR cs.SE 89%

Think Broad, Act Narrow: CWE Identification with Multi-Agent Large Language Models

Mohammed Sayagh, Mohammad Ghafari

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2508.01402 2025-08-05 cs.CV 89%

ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models

Chuangchuang Tan, Jinglu Wang, Xiang Ming, Renshuai Tao, Yunchao Wei, Yao Zhao, Yan Lu

机构 * Beijing Jiaotong University（北京交通大学）； Microsoft Research Asia（微软亚洲研究院）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2508.01554 2025-08-05 cs.CL cs.AI cs.CR 88%

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models

Yujia Zheng, Tianhao Li, Haotian Huang, Tianyu Zeng, Jingyu Lu, Chuangxin Chu, Yuekai Huang, Ziyou Jiang, Qian Xiong, Yuyao Ge, Mingyang Li

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

2508.01006 2025-08-05 cs.CL 88%

UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu

Farah Adeeba, Brian Dillon, Hassan Sajjad, Rajesh Bhatt

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2505.16326 2025-08-05 cs.LG 88%

ChemMLLM: Chemical Multimodal Large Language Model

Qian Tan, Dongzhan Zhou, Peng Xia, Wanhao Liu, Wanli Ouyang, Lei Bai, Yuqiang Li, Tianfan Fu

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；分类 cs.LG

Comments 23 pages

2502.19166 2025-08-05 cs.SE cs.LG 88%

CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation

Kaiwen Yan, Hongcheng Guo, Xuanqing Shi, Shaosheng Cao, Donglin Di, Zhoujun Li

机构 * Beihang University（北航大学）； Tsinghua University（清华大学）； Xiaohongshu（小红书）

专题命中评测与基准：large language model(title,abstract)；language model(title,abstract)；分类 cs.LG

Comments Accepted as an ACL 2025 Industry Track paper (15 pages)

2508.01685 2025-08-05 cs.LG cs.CR 87%

Innovative tokenisation of structured data for LLM training

Kayvan Karim, Hani Ragab Hassen. Hadj Batatia

机构 * School of Mathematics and Computer Science（数学与计算机科学学院）

专题命中评测与基准：LLM(title,abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

1. 推理与问题求解 41 篇

WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning

Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning

Hierarchical Reasoning Model

Distributed AI Agents for Cognitive Underwater Robot Autonomy

Do AI models help produce verified bug fixes?

Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models

Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice

Towards Zero-Shot Terrain Traversability Estimation: Challenges and Opportunities

Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework

Describe Anything Model for Visual Question Answering on Text-rich Images

KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks

Multi-Object Sketch Animation by Scene Decomposition and Motion Planning

2. 评测与基准 84 篇

Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting

A Survey on Data Security in Large Language Models

Am I Blue or Is My Hobby Counting Teardrops? Expression Leakage in Large Language Models as a Symptom of Irrelevancy Disruption

SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models

AI-Based Measurement of Innovation: Mapping Expert Insight into Large Language Model Applications

End-to-End Personalization: Unifying Recommender Systems with Large Language Models

Automated Label Placement on Maps via Large Language Models

LLMs on Trial: Evaluating Judicial Fairness for Large Language Models

Correctness Assessment of Code Generated by Large Language Models Using Internal Representations

Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?

Think Broad, Act Narrow: CWE Identification with Multi-Agent Large Language Models

ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models

UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu

ChemMLLM: Chemical Multimodal Large Language Model

CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation

Innovative tokenisation of structured data for LLM training