arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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。

2025-09-29 至 2025-09-29 共收录 107 信号源:cs.CL, cs.AI, cs.LG

1. 数学推理 6 篇

2505.12833 2025-09-29 cs.AI 79%

Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs

Zhuo Yang, Daolang Wang, Lingli Ge, Beilun Wang, Tianfan Fu, Yuqiang Li

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Xidian University(西安电子科技大学) North University of China(北方大学) Fudan University(复旦大学) Southeast University(东南大学) Nanjing University(南京大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21854 2025-09-29 cs.MM cs.CV 78%

Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization

Songjun Tu, Qichao Zhang, Jingbo Sun, Yuqian Fu, Linjing Li, Xiangyuan Lan, Dongmei Jiang, Yaowei Wang, Dongbin Zhao

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院) Pengcheng Laboratory(鹏城实验室) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))

专题命中 数学推理 :reasoning(title,abstract)

Comments 12pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.20016 2025-09-29 cs.CL 77%

Vulnerability of LLMs to Vertically Aligned Text Manipulations

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Zhen Xiong, Nanyun Peng, Kai-wei Chang

机构 * University of California, San Diego(加州大学圣地亚哥分校) University of California, Los Angeles(加州大学洛杉矶分校) The University of Queensland(昆士兰大学) National University of Singapore(新加坡国立大学) University of Southern California(南加州大学) University of California, Merced(加州大学默塞德分校)

专题命中 数学推理 :reasoning(abstract);chain-of-thought(abstract);CoT(abstract);分类 cs.CL

Comments Accepted to ACL 2025 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08799 2025-09-29 cs.CL cs.AI 73%

KV Cache Steering for Controlling Frozen LLMs

Max Belitsky, Dawid J. Kopiczko, Michael Dorkenwald, M. Jehanzeb Mirza, James R. Glass, Cees G. M. Snoek, Yuki M. Asano

机构 * VIS Lab, University of Amsterdam(阿姆斯特丹大学VIS实验室) FunAI Lab, University of Technology Nuremberg(纽伦堡技术大学FunAI实验室) CSAIL, Massachusetts Institute of Technology(麻省理工学院计算机科学与人工智能实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21792 2025-09-29 cs.LG cs.AI 62%

FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning

Yizhou Zhang, Ning Lv, Teng Wang, Jisheng Dang

机构 * Lanzhou University(兰州大学) The University of Hong Kong(香港大学) National University of Singapore(新加坡国立大学)

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

Comments Submitted to ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12716 2025-09-29 cs.CL cs.AI 62%

Shadow-FT: Tuning Instruct Model via Training on Paired Base Model

Taiqiang Wu, Runming Yang, Jiayi Li, Pengfei Hu, Yik-Chung Wu, Ngai Wong, Yujiu Yang

机构 * The University of Hong Kong(香港大学) Tsinghua University(清华大学) Tencent(腾讯)

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

Comments 24 pages, 12 tables, 8 figures. Previous name: Shadow-FT: Tuning Instruct via Base

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 逻辑推理 4 篇

2509.17978 2025-09-29 cs.AI cs.LO 83%

The STAR-XAI Protocol: A Framework for Inducing and Verifying Agency, Reasoning, and Reliability in AI Agents

Antoni Guasch, Maria Isabel Valdez

机构 * Ixent Games

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

Comments Version 2: This article consolidates and replaces a previous version to present the complete research in a single, comprehensive manuscript

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21874 2025-09-29 cs.LG 70%

Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models

Yifei Peng, Yaoli Liu, Enbo Xia, Yu Jin, Wang-Zhou Dai, Zhong Ren, Yao-Xiang Ding, Kun Zhou

机构 * State Key Laboratory of CAD&CG(计算机辅助设计与图形学国家重点实验室) National Key Laboratory for Novel Software Technology(新型软件技术国家实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22119 2025-09-29 cs.CL cs.AI 62%

Universal Legal Article Prediction via Tight Collaboration between Supervised Classification Model and LLM

Xiao Chi, Wenlin Zhong, Yiquan Wu, Wei Wang, Kun Kuang, Fei Wu, Minghui Xiong

机构 * Zhejiang University(浙江大学)

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

Comments 10 pages, 6 figures, Accepted to ICAIL 2025 (International Conference on Artificial Intelligence and Law)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22537 2025-09-29 cs.AI 57%

The Emergence of Altruism in Large-Language-Model Agents Society

Haoyang Li, Xiao Jia, Zhanzhan Zhao

机构 * Department of Sociology(社会学系) School of Artificial Intelligence(人工智能学院) School of Humanities and Social Science(人文社会科学学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 规划推理 21 篇

2509.21662 2025-09-29 cs.LG 92%

MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning

Afrina Tabassum, Bin Guo, Xiyao Ma, Hoda Eldardiry, Ismini Lourentzou

机构 * Amazon(亚马逊公司) Alexa, Amazon(亚马逊Alexa部门) Virginia Tech(弗吉尼亚理工大学) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

专题命中 规划推理 :reasoning(title,abstract);chain-of-thought(title,abstract);planning(title,abstract);CoT(abstract)

Comments 17 pages, 9 figures, 14 tables, Findings of the Association for Computational Linguistics: EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.20988 2025-09-29 cs.AI q-bio.QM 83%

AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search

Xiaozhuang Song, Xuanhao Pan, Xinjian Zhao, Hangting Ye, Shufei Zhang, Jian Tang, Tianshu Yu

机构 * School of Data Science, CUHK-Shenzhen(CUHK-Shenzhen数据科学学院) Shanghai AI Laboratory(上海人工智能实验室) Jilin University(吉林大学) Mila - Quebec AI Institute(魁北克AI研究所) HEC Montréal(蒙特利尔HEC)

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

Comments 34 pages, 21 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22572 2025-09-29 cs.AI cs.CL cs.LG 82%

Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time

Yixuan Han, Fan Ma, Ruijie Quan, Yi Yang

机构 * Zhejiang University(浙江大学) Nanyang Technological University(南洋理工大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21482 2025-09-29 cs.CL cs.AI cs.LG 75%

Learning to Reason with Mixture of Tokens

Adit Jain, Brendan Rappazzo

机构 * Machine Learning Research, Morgan Stanley, New York, NY(机器学习研究部,摩根士丹利,纽约,纽约) School of Electrical and Computer Engineering, Cornell University, Ithaca, NY(电气与计算机工程学院,康奈尔大学,伊萨卡,纽约)

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

Comments 30 page

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21324 2025-09-29 cs.IR cs.AI 74%

From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data

Gurbinder Gill, Ritvik Gupta, Denis Lusson, Anand Chandrashekar, Donald Nguyen

机构 * Corvic AI Inc(Corvic AI公司)

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
2509.22137 2025-09-29 cs.AI cs.HC cs.MA cs.RO 70%

Log2Plan: An Adaptive GUI Automation Framework Integrated with Task Mining Approach

Seoyoung Lee, Seonbin Yoon, Seongbeen Lee, Hyesoo Kim, Joo Yong Sim

机构 * Sookmyung Women's University(首尔女子大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21733 2025-09-29 cs.CV cs.AI cs.CL cs.HC cs.LG 67%

UISim: An Interactive Image-Based UI Simulator for Dynamic Mobile Environments

Jiannan Xiang, Yun Zhu, Lei Shu, Maria Wang, Lijun Yu, Gabriel Barcik, James Lyon, Srinivas Sunkara, Jindong Chen

机构 * University of California, San Diego (UCSD)(加州大学圣地亚哥分校) Google DeepMind(谷歌DeepMind)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22130 2025-09-29 cs.MA cs.AI cs.LG 62%

Multi-Agent Path Finding via Offline RL and LLM Collaboration

Merve Atasever, Matthew Hong, Mihir Nitin Kulkarni, Qingpei Li, Jyotirmoy V. Deshmukh

机构 * Department of Computer Science, University of Southern California(计算机科学系,南加州大学)

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
2508.00719 2025-09-29 cs.CL cs.AI 62%

DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS

Yingxu Wang, Shiqi Fan, Mengzhu Wang, Siyang Gao, Chao Wang, Nan Yin

机构 * MBZUAI PolyU Hebei University of Technology(河北工业大学) CityU(城市大学) HKUST(香港科技大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23537 2025-09-29 cs.LG cs.CL 62%

Domain-Aware Tensor Network Structure Search

Giorgos Iacovides, Wuyang Zhou, Chao Li, Qibin Zhao, Danilo Mandic

机构 * Department of Electrical and Electronic Engineering, Imperial College London(帝国理工学院伦敦校区电子与电气工程系) RIKEN AIP(日本理化学研究所AIP)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22008 2025-09-29 cs.LG 57%

Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning

Yajie Qi, Wei Wei, Lin Li, Lijun Zhang, Zhidong Gao, Da Wang, Huizhong Song

机构 * School of Computer and Information Technology, Shanxi University(计算机与信息技术学院,山西大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.20253 2025-09-29 cs.RO cs.AI 57%

AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving

Jinhao Chai, Anqing Jiang, Hao Jiang, Shiyi Mu, Zichong Gu, Hao Sun, Shugong Xu

机构 * School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China(信息工程学院,上海大学) Bosch Corporate Research, Bosch (China) Investment Ltd., Shanghai, China(博世企业研究,博世(中国)投资有限公司) School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China(机械工程学院,上海交通大学) Xi'an Jiaotong-Liverpool University, Suzhou, China(西安交通大学利物浦大学)

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
2508.08524 2025-09-29 cs.HC cs.AI 57%

StreetReaderAI: Making Street View Accessible Using Context-Aware Multimodal AI

Jon E. Froehlich, Alexander Fiannaca, Nimer Jaber, Victor Tsaran, Shaun Kane

机构 * Google Research(谷歌研究) Google DeepMind(谷歌DeepMind) Google(谷歌)

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

Comments Accepted to UIST'25; v2. Fixed a missing word in the PDF; v3. Fixed a typo in an author's name; v4. Changed system name and title

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21279 2025-09-29 cs.AI 57%

XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State Level

Shaoqing Zhang, Kehai Chen, Zhuosheng Zhang, Rumei Li, Rongxiang Weng, Yang Xiang, Min Zhang

机构 * Harbin Institute of Technology(哈尔滨工业大学) Pengcheng Laboratory(鹏城实验室) Shanghai Jiao Tong University(上海交通大学) Meituan(美团)

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
2504.12633 2025-09-29 cs.CL 57%

SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs

Younghun Lee, Dan Goldwasser

机构 * Department of Computer Science(计算机科学系)

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

Comments Accepted to the Main Conference at EMNLP 2025. 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02519 2025-09-29 cs.CL 57%

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent

Xingzuo Li, Kehai Chen, Yunfei Long, Xuefeng Bai, Yong Xu, Min Zhang

机构 * School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China(计算机科学与技术学院,哈尔滨工业大学深圳校区) School of Electronic Engineering and Computer Science, Queen Mary University of London(电子工程与计算机科学学院,Queen Mary大学伦敦校区)

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

Comments EMNLP 2025 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21358 2025-09-29 cs.CV cs.AI 57%

MDF-MLLM: Deep Fusion Through Cross-Modal Feature Alignment for Contextually Aware Fundoscopic Image Classification

Jason Jordan, Mohammadreza Akbari Lor, Peter Koulen, Mei-Ling Shyu, Shu-Ching Chen

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

Comments Word count: 5157, Table count: 2, Figure count: 5

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21873 2025-09-29 cs.RO 50%

Improved Vehicle Maneuver Prediction using Game Theoretic Priors

Nishant Doshi

专题命中 规划推理 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21523 2025-09-29 cs.RO 50%

DroneFL: Federated Learning for Multi-UAV Visual Target Tracking

Xiaofan Yu, Yuwei Wu, Katherine Mao, Ye Tian, Vijay Kumar, Tajana Rosing

机构 * University of Pennsylvania(宾夕法尼亚大学) Department of Electrical Engineering, University of California at Merced(电气工程系,加州大学默塞德分校)

专题命中 规划推理 :planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21507 2025-09-29 cs.CE 50%

QuantMind: A Context-Engineering Based Knowledge Framework for Quantitative Finance

Haoxue Wang, Keli Wen, Yuante Li, Qiancheng Qu, Xiangxu Mu, Xinjie Shen, Jiaqi Gao, Chenyang Chang, Chuhan Xie, San Yu Cheung, Zhuoyuan Hu, Xinyu Wang, Sirui Bi, Bi'an Du

专题命中 规划推理 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏