语言大模型 / LLM - arXivDaily 专题

2510.04695 2025-10-07 cs.AI 83%

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents

Yiding Wang, Zhepei Wei, Xinyu Zhu, Yu Meng

机构 * Department of Computer Science, University of Virginia（计算机科学系，弗吉尼亚大学）

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

2507.16856 2025-10-07 cs.CV cs.AI 83%

SIA: Enhancing Safety via Intent Awareness for Vision-Language Models

Youngjin Na, Sangheon Jeong, Youngwan Lee, Jian Lee, Dawoon Jeong, Youngman Kim

机构 * VLM Safety LAB, MODULABS（视觉语言模型安全实验室，MODULABS）； ETRI（电子技术研究院）； KAIST（韩国科学技术院）

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

Comments Accepted to Safe and Trustworthy Multimodal AI Systems(SafeMM-AI) Workshop at ICCV2025, Non-archival track

2502.11723 2025-10-07 cs.AI 83%

Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption

Alireza Nik, Michael A. Riegler, Pål Halvorsen

机构 * SimulaMet

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

Comments Updated version with additional models and benchmark datasets. The experimental section has been expanded with new analyses, and minor corrections and clarifications have been made throughout the text

2505.01479 2025-10-07 cs.CL 83%

Deliberate Planning in Language Models with Symbolic Representation

Siheng Xiong, Zhangding Liu, Jieyu Zhou, Yusen Su

机构 * Georgia Institute of Technology, Atlanta, GA 30332 USA（佐治亚理工学院）

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

Comments Accepted to Twelfth Annual Conference on Advances in Cognitive Systems

2502.15153 2025-10-03 cs.CL 83%

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements

Tianjie Ju, Bowen Wang, Hao Fei, Mong-Li Lee, Wynne Hsu, Yun Li, Qianren Wang, Pengzhou Cheng, Zongru Wu, Haodong Zhao, Zhuosheng Zhang, Gongshen Liu

机构 * Shanghai Jiao Tong University（上海交通大学）； National University of Singapore（新加坡国立大学）； Cognitive AI Lab（认知人工智能实验室）

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

Comments Working in progress

2510.00881 2025-10-02 cs.SE cs.AI 83%

Advancing Automated Ethical Profiling in SE: a Zero-Shot Evaluation of LLM Reasoning

Patrizio Migliarini, Mashal Afzal Memon, Marco Autili, Paola Inverardi

机构 * University of L'Aquila（拉奎拉大学）； Gran Sasso Science Institute（格兰萨索科学研究所）

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

Comments Accepted at ASE 2025

2509.06952 2025-09-30 cs.CL 83%

On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts

Linlu Qiu, Cedegao E. Zhang, Joshua B. Tenenbaum, Yoon Kim, Roger P. Levy

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）； MIT BCS（麻省理工学院脑科学与认知研究中心）

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

Comments EMNLP 2025 (Main)

2505.15298 2025-09-30 cs.RO cs.CL cs.CV 83%

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动学院）； McGill University（麦吉尔大学）； Automotive and Robotics, Xiaomi Corporation（小米公司汽车与机器人部门）； University of Wisconsin-Madison（威斯康星大学麦迪逊分校）

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

Comments 19 pages, 8 figures

Journal ref EMNLP2025 Fundings

2504.15241 2025-09-29 cs.CL 83%

MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety

Yahan Yang, Soham Dan, Shuo Li, Dan Roth, Insup Lee

机构 * University of Pennsylvania（宾夕法尼亚大学）； Microsoft（微软公司）； Oracle AI

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

Comments Preprint

2505.18961 2025-09-25 cs.AI cs.IR 83%

Weaver: Interweaving SQL and LLM for Table Reasoning

Rohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth, Vivek Gupta

机构 * Arizona State University（亚利桑那州立大学）； University of Pennsylvania（宾夕法尼亚大学）

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

2509.18163 2025-09-24 cs.CL 83%

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning

Haodong Zhao, Chenyan Zhao, Yansi Li, Zhuosheng Zhang, Gongshen Liu

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）

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

Comments Work in progress

2505.18555 2025-09-24 cs.CL 83%

Unraveling Misinformation Propagation in LLM Reasoning

Yiyang Feng, Yichen Wang, Shaobo Cui, Boi Faltings, Mina Lee, Jiawei Zhou

机构 * EPFL（瑞士联邦理工学院）； Stony Brook University（史泰士布鲁克大学）； University of Chicago（芝加哥大学）

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

Comments Accepted to EMNLP 2025 (Findings)

2509.18063 2025-09-23 cs.CL 83%

ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning

Jan-Felix Klein, Lars Ohnemus

机构 * Institute of Material Handling and Logistics (IFL) at the Karlsruhe Institute of Technology (KIT)（材料搬运与物流研究所（IFL）于卡尔斯鲁厄理工学院（KIT））

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

Comments Work in Progess

2509.17570 2025-09-23 cs.CL 83%

Asking a Language Model for Diverse Responses

Sergey Troshin, Irina Saparina, Antske Fokkens, Vlad Niculae

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

Comments UncertaiNLP workshop, 2025

2509.16533 2025-09-23 cs.CL 83%

Challenging the Evaluator: LLM Sycophancy Under User Rebuttal

Sungwon Kim, Daniel Khashabi

机构 * Johns Hopkins University（约翰霍普金斯大学）

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

Comments Accepted to EMNLP 2025 Findings

2506.12935 2025-09-23 cs.CL cs.MM cs.SD eess.AS 83%

SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models

Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Peijun Qing, Soroush Vosoughi, Jiang Gui

机构 * Dartmouth College（达特茅斯学院）； Shandong University（山东大学）

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

Comments Accepted to EMNLP 2025 Main Conference (Oral Presentation)

2505.08364 2025-09-18 cs.AI 83%

Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation

Enci Zhang, Xingang Yan, Wei Lin, Tianxiang Zhang, Qianchun Lu

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

Comments 14 pages, 3 figs

2407.11963 2025-09-18 cs.CL 83%

NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities

Mo Li, Songyang Zhang, Taolin Zhang, Haodong Duan, Yunxin Liu, Kai Chen

机构 * Tsinghua University（清华大学）； Shanghai AI Laboratory（上海人工智能实验室）

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

Comments v3: Revisions with added experiments, clarifications, and related work updates

2509.12914 2025-09-17 cs.AI 83%

Stochastic Streets: A Walk Through Random LLM Address Generation in four European Cities

Tairan Fu, David Campo-Nazareno, Javier Coronado-Blázquez, Javier Conde, Pedro Reviriego, Fabrizio Lombardi

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

2509.12798 2025-09-17 cs.SE cs.AI 83%

LLM-Based Approach for Enhancing Maintainability of Automotive Architectures

Nenad Petrovic, Lukasz Mazur, Alois Knoll

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

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

2505.14172 2025-09-17 cs.CL 83%

The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models

Adrian Cosma, Stefan Ruseti, Emilian Radoi, Mihai Dascalu

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

Comments Accepted at EMNLP 2025 Main as Oral Presentation (Top 15% of accepted papers)

2509.10249 2025-09-15 cs.AI 83%

Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering

Hanna Abi Akl

机构 * Université Côte d’Azur（法国滨海大学）； Inria（法国国家信息与自动化技术研究所）； CNRS（法国国家科学研究中心）； I3S（国际科学计算研究所）； Sophia Antipolis, France（法国索菲亚大学）； Data ScienceTech Institute (DSTI)（数据科学技术研究所）

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

Comments accepted for the International Joint Conference on Rules and Reasoning (RuleML+RR) 2025

2509.09731 2025-09-15 cs.CL 83%

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning

Haiyang Yu, Yuchuan Wu, Fan Shi, Lei Liao, Jinghui Lu, Xiaodong Ge, Han Wang, Minghan Zhuo, Xuecheng Wu, Xiang Fei, Hao Feng, Guozhi Tang, An-Lan Wang, Hanshen Zhu, Yangfan He, Quanhuan Liang, Liyuan Meng, Chao Feng, Can Huang, Jingqun Tang, Bin Li

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

2506.10106 2025-09-15 cs.RO cs.AI 83%

One For All: LLM-based Heterogeneous Mission Planning in Precision Agriculture

Marcos Abel Zuzuárregui, Mustafa Melih Toslak, Stefano Carpin

机构 * Department of Computer Science（计算机科学系）； Engineering University of California, Merced, CA, USA.（加州大学默塞德分校工程学院）； Department of Informatics, Bioengineering, Robotics（信息学、生物工程、机器人学系）； Systems Engineering, University of Genova, Italy（系统工程系，热那亚大学）

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

Comments Accepted to International Federation of Automatic Control (IFAC) Sensing, Control and Automation Technologies for Agriculture - 8th AGRICONTROL 2025

Journal ref International Federation of Automatic Control (IFAC) Sensing, Control and Automation Technologies for Agriculture - 8th AGRICONTROL 2025

2509.07763 2025-09-10 cs.SE cs.AI cs.PL 83%

What Were You Thinking? An LLM-Driven Large-Scale Study of Refactoring Motivations in Open-Source Projects

Mikel Robredo, Matteo Esposito, Fabio Palomba, Rafael Peñaloza, Valentina Lenarduzzi

机构 * University of Oulu（奥卢大学）； University of Salerno（萨勒诺大学）； University of Milano-Bicocca（米兰-布雷塞大学）

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

2508.05702 2025-09-10 cs.MA cs.AI cs.SY eess.SY 83%

Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control

Yan Zhang, Ahmad Mohammad Saber, Amr Youssef, Deepa Kundur

机构 * Department of Electrical and Computer Engineering, University of Toronto（电气与计算机工程系，多伦多大学）； Concordia Institute for Information Systems Engineering（康卡迪亚信息系统工程研究所）； Concordia University（康卡迪亚大学）

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

2509.00054 2025-09-09 cs.RO cs.AI 83%

Robotic Fire Risk Detection based on Dynamic Knowledge Graph Reasoning: An LLM-Driven Approach with Graph Chain-of-Thought

Haimei Pan, Jiyun Zhang, Qinxi Wei, Xiongnan Jin, Chen Xinkai, Jie Cheng

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

Comments We have decided to withdraw this paper as the work is still undergoing further refinement. To ensure the clarity of the results, we prefer to make additional improvements before resubmission. We appreciate the readers' understanding

2509.00664 2025-09-03 cs.CV cs.AI 83%

Fusion to Enhance: Fusion Visual Encoder to Enhance Multimodal Language Model

Yifei She, Huangxuan Wu

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）

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

2509.00125 2025-09-03 cs.AI 83%

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning

Ang Li, Zhihang Yuan, Yang Zhang, Shouda Liu, Yisen Wang

机构 * PKU（北京大学）； ByteDance Seed（字节跳动种子）

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

2503.11302 2025-08-29 cs.CL 83%

Are formal and functional linguistic mechanisms dissociated in language models?

Michael Hanna, Yonatan Belinkov, Sandro Pezzelle

机构 * Institute for Logic, Language and Computation University of Amsterdam（逻辑、语言与计算研究所阿姆斯特丹大学）； Technion – Israel Institute of Technology（技术ion-以色列理工学院）

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

Comments To appear in Computational Linguistics. Pre-MIT Press publication version. 40 pages, 14 figures, 3 tables. Code available at https://github.com/hannamw/formal-functional-dissociation

1. 推理与问题求解 18971 篇

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents

SIA: Enhancing Safety via Intent Awareness for Vision-Language Models

Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption

Deliberate Planning in Language Models with Symbolic Representation

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements

Advancing Automated Ethical Profiling in SE: a Zero-Shot Evaluation of LLM Reasoning

On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving

MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety

Weaver: Interweaving SQL and LLM for Table Reasoning

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning

Unraveling Misinformation Propagation in LLM Reasoning

ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning

Asking a Language Model for Diverse Responses

Challenging the Evaluator: LLM Sycophancy Under User Rebuttal

SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models

Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation

NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities

Stochastic Streets: A Walk Through Random LLM Address Generation in four European Cities

LLM-Based Approach for Enhancing Maintainability of Automotive Architectures

The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models

Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning

One For All: LLM-based Heterogeneous Mission Planning in Precision Agriculture

What Were You Thinking? An LLM-Driven Large-Scale Study of Refactoring Motivations in Open-Source Projects

Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control

Robotic Fire Risk Detection based on Dynamic Knowledge Graph Reasoning: An LLM-Driven Approach with Graph Chain-of-Thought

Fusion to Enhance: Fusion Visual Encoder to Enhance Multimodal Language Model

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning

Are formal and functional linguistic mechanisms dissociated in language models?