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。

共收录 45051 信号源:cs.CL, cs.AI, cs.LG

1. 逻辑推理 3033 篇

2603.25077 2026-03-27 cs.CV 78%

Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs

弥合感知与推理:用于多模态大语言模型中RLVR的标记重加权

Jinda Lu, Junkang Wu, Jinghan Li, Kexin Huang, Shuo Yang, Guoyin Wang, Jiancan Wu, Xiang Wang, Xiangnan He

机构 * University of Science and Technology of China(中国科学技术大学) Peking University(北京大学) Independent Researcher(独立研究员)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出Token-Reweighting策略,通过动态重加权多模态大语言模型中的感知与推理标记,提升RLVR性能,实现视觉 grounding 和推理的协同优化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18463 2026-03-13 cs.CV 78%

Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding

解耦感知与推理以实现抗幻觉的视频理解

Bowei Pu, Chuanbin Liu, Yifan Ge, Peicheng Zhou, Yiwei Sun, Zhiying Lu, Zhangchi Hu, Hongtao Xie

机构 * University of Science and Technology of China(中国科学技术大学)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出DPL模型,通过解耦感知与推理以提升视频理解的抗幻觉能力,引入感知奖励和FAE评估器,有效提高训练后性能和数据效率。

Comments 17 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.09246 2026-03-11 cs.CR 78%

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models

面向推理的编程:通过链式语义工具来突破大型视觉语言模型

Quanchen Zou, Moyang Chen, Zonghao Ying, Wenzhuo Xu, Yisong Xiao, Deyue Zhang, Dongdong Yang, Zhao Liu, Xiangzheng Zhang

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出面向推理的编程方法,通过链式语义工具突破大型视觉语言模型的安全对齐。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.22923 2026-02-27 cs.CV cs.RO 78%

WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents

WaterVideoQA: 以ASV为中心的感知与符合规则的推理 via 多模态智能体

Runwei Guan, Shaofeng Liang, Ningwei Ouyang, Weichen Fei, Shanliang Yao, Wei Dai, Chenhao Ge, Penglei Sun, Xiaohui Zhu, Tao Huang, Ryan Wen Liu, Hui Xiong

机构 * Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)(香港理工大学(广州)人工智能研究所) Hubei Key Laboratory of Inland Shipping Technology (Wuhan University of Technology)(湖北内河航运技术重点实验室(武汉理工大学)) School of Navigation, Wuhan University of Technology(武汉理工大学航海学院) School of Advanced Technology, Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学先进科技学院) School of Artificial Intelligence, Nanjing University(南京大学人工智能学院) School of Information Engineering, Yancheng Institute of Technology(盐城职业技术学院信息工程学院) School of Engineering, Stanford University(斯坦福大学工程学院) Centre for AI and Data Science Innovation and the School of Science and Engineering, James Cook University(詹姆斯库克大学人工智能与数据科学创新中心及科学与工程学院)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 WaterVideoQA通过多模态智能体系统,实现ASV在复杂水域环境中的感知与规则合规推理,提升自主航行的安全性和精确性。

Comments 11 pages,8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21190 2026-02-19 cs.CR 78%

The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning

恶意示例:通过模板填充和不安全推理实现大语言模型的劫持

Mingrui Liu, Sixiao Zhang, Cheng Long, Kwok Yan Lam

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 TrojFill通过模板填充和不安全推理漏洞,实现对大语言模型的安全过滤绕过,展示了对齐LLM的系统性弱点。

Comments under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22120 2026-02-06 cs.CV 78%

See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning

看得少,看得对:双向感知塑造用于多模态推理

Shuoshuo Zhang, Yizhen Zhang, Jingjing Fu, Lei Song, Jiang Bian, Yujiu Yang, Rui Wang

机构 * Microsoft Research Asia(微软亚洲研究院) Tsinghua University(清华大学)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出BiPS,通过双向感知塑造提升多模态推理性能,有效增强细粒度视觉依赖并提升跨领域泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00675 2026-02-03 cs.RO cs.HC 78%

Factored Reasoning with Inner Speech and Persistent Memory for Evidence-Grounded Human-Robot Interaction

基于内部言语和持久记忆的因子推理用于证据导向的人机交互

Valerio Belcamino, Mariya Kilina, Alessandro Carfì, Valeria Seidita, Fulvio Mastrogiovanni, Antonio Chella

机构 * Department of Engineering, University of Palermo(帕尔米罗大学工程系) TheEngineRoom, Department of Informatics Bioengineering, Robotics and System Engineering(TheEngineRoom,信息生物工程、机器人与系统工程系)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 JANUS 通过因子推理实现证据导向的人机交互,结合内部言语和持久记忆模块,提升机器人辅助系统的可扩展性和可审计性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14957 2026-01-29 cs.CV 78%

Neuro Symbolic Knowledge Reasoning for Procedural Video Question Answering

用于过程视频问答的神经符号知识推理

Basura Fernando, Thanh-Son Nguyen, Hong Yang, Tzeh Yuan Neoh, Hao Zhang, Ee Yeo Keat

机构 * Centre for Frontier AI Research, A*STAR, Singapore(前沿人工智能研究所以(A*STAR)) Institute of High-Performance Computing, A*STAR, Singapore(高性能计算研究所(A*STAR)) College of Computing and Data Science, NTU, Singapore(计算与数据科学学院(NTU))

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出KML框架,通过神经符号方法提升过程视频问答的推理能力,结合知识图谱实现可解释的多步骤推理。

Comments This paper is under review at IEEE Transactions on Neural Networks and Learning Systems. Personal use is permitted, but republication/redistribution requires IEEE permission

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11322 2026-01-19 cs.CV cs.LO 78%

Enhancing Vision Language Models with Logic Reasoning for Situational Awareness

通过逻辑推理增强视觉语言模型以提升情境感知能力

Pavana Pradeep, Krishna Kant, Suya Yu

机构 * CIS Department, Temple University(Temple大学计算机与信息科学系) ARL(美国陆军研究实验室)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文通过整合逻辑推理与传统计算机视觉方法,提升视觉语言模型在情境感知中的准确性与细粒度事件识别能力。

Comments Accepted for publication in IEEE Transactions on AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08440 2026-01-14 cs.CV 78%

Incentivizing Cardiologist-Like Reasoning in MLLMs for Interpretable Echocardiographic Diagnosis

激励MLLMs实现类似心内科医生的推理以实现可解释的超声心动图诊断

Yi Qin, Lehan Wang, Chenxu Zhao, Alex P. W. Lee, Xiaomeng Li

机构 * The Hong Kong University of Science and Technology(香港科学与技术大学) The Chinese University of Hong Kong(香港中文大学)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出CRT和CardiacMind,通过引入心内科医生的思维模式,提升MLLMs在超声心动图诊断中的推理能力,实现48%的诊断性能提升。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.08930 2026-01-08 cs.GR 78%

How Does a Virtual Agent Decide Where to Look? Symbolic Cognitive Reasoning for Embodied Head Rotation

虚拟代理如何决定看向何处?基于具身头部旋转的符号认知推理

Juyeong Hwang, Seong-Eun Hong, JaeYoung Seon, Hyeongyeop Kang

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出SCORE框架,通过符号认知推理实现具身头部旋转,结合视觉-语言模型和大语言模型,使虚拟代理能合理预测头部运动及背后动机。

Comments 13 pages, 8 figures. Accepted to SIGGRAPH Asia Conference Papers '25

Journal ref SIGGRAPH Asia Conference Papers '25, December 15-18, 2025, Hongkong

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12656 2025-12-16 cs.LO 78%

Argumentative Reasoning with Language Models on Non-factorized Case Bases

基于非因子化案例库的语言模型论证推理

Wachara Fungwacharakorn, May Myo Zin, Ha-Thanh Nguyen, Yuntao Kong, Ken Satoh

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出AAM-CBR框架,通过语言模型实现非因子化案例库的基于案例推理,提升灵活性和隐私性,并展示在因素数量增加时需结合符号推理以提高效果。

Comments Presented at NeLaMKRR@KR, 2025 (arXiv:2511.09575)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07811 2025-12-12 cs.CV 78%

Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning

超越可见线索:通过双线索推理进行隐式视频问答

Tieyuan Chen, Huabin Liu, Yi Wang, Chaofan Gan, Mingxi Lyu, Ziran Qin, Shijie Li, Liquan Shen, Junhui Hou, Zheng Wang, Weiyao Lin

机构 * Shanghai Jiao Tong University(上海交通大学) ZhongguanCun Academy(中关村学院) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Shanghai University(上海大学) City University of Hong Kong(香港城市大学) Wuhan University(武汉大学)

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出隐式视频问答任务和IRM模型,通过双线索推理提升隐式问答性能,优于现有模型。

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18531 2025-12-01 cs.CR cs.PL 78%

LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs

LockForge: 基于多智能体推理LLM的逻辑锁纸到代码自动化

Akashdeep Saha, Zeng Wang, Prithwish Basu Roy, Johann Knechtel, Ozgur Sinanoglu, Ramesh Karri

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 LockForge通过多智能体推理LLM自动化将逻辑锁论文描述转换为可执行代码,解决可重复性难题,提供系统化验证框架和基准测试。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16369 2025-11-21 eess.SP cs.NI 78%

Reasoning Meets Representation: Envisioning Neuro-Symbolic Wireless Foundation Models

推理与表征的结合:展望神经符号无线基础模型

Jaron Fontaine, Mohammad Cheraghinia, John Strassner, Adnan Shahid, Eli De Poorter

专题命中 逻辑推理 :reasoning(title,abstract)

AI总结 本文提出神经符号无线基础模型,结合神经网络与符号推理,以解决无线通信中的可解释性、鲁棒性和合规性问题,推动6G网络的智能化发展。

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12543 2025-11-18 cs.SE 78%

High-level reasoning while low-level actuation in Cyber-Physical Systems: How efficient is it?

Burak Karaduman, Baris Tekin Tezel, Moharram Challenger

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11187 2025-11-17 cs.HC 78%

ReTrace: Interactive Visualizations for Reasoning Traces of Large Reasoning Models

Ludwig Felder, Jacob Miller, Markus Wallinger, Stephen Kobourov, Chunyang Chen

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18041 2025-11-17 cs.CV 78%

NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning

Sahil Shah, S P Sharan, Harsh Goel, Minkyu Choi, Mustafa Munir, Manvik Pasula, Radu Marculescu, Sandeep Chinchali

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06483 2025-11-11 cs.SD 78%

SAR-LM: Symbolic Audio Reasoning with Large Language Models

Termeh Taheri, Yinghao Ma, Emmanouil Benetos

机构 * School of Electronic Engineering(电子工程学院) Computer Science, Queen Mary University of London, London, United Kingdom(计算机科学,伦敦大学玛丽女王学院,伦敦,英国)

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.15841 2025-10-20 cs.CV 78%

Neuro-Symbolic Spatial Reasoning in Segmentation

Jiayi Lin, Jiabo Huang, Shaogang Gong

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.07957 2025-09-10 cs.RO 78%

Graph-Fused Vision-Language-Action for Policy Reasoning in Multi-Arm Robotic Manipulation

Shunlei Li, Longsen Gao, Jiuwen Cao, Yingbai Hu

机构 * Machine Learning and I-health International Cooperation Base of Zhejiang Province, Artificial Intelligence Institute, Hangzhou Dianzi University, Zhejiang(浙江省机器学习与健康国际合作基地、人工智能学院、杭州电子大学) Electrical and Computer Engineering Department, The University of New Mexico(新墨西哥大学电气与计算机工程系) School of Computation, Information and Technology, Technical University of Munich(慕尼黑技术大学计算、信息与技术学院)

专题命中 逻辑推理 :reasoning(title,abstract)

Comments This paper is submitted to IEEE IROS 2025 Workshop AIR4S

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.19429 2025-08-28 cs.RO cs.FL 78%

An Iterative Approach for Heterogeneous Multi-Agent Route Planning with Resource Transportation Uncertainty and Temporal Logic Goals

Gustavo A. Cardona, Kaier Liang, Cristian-Ioan Vasile

机构 * Mechanical Engineering and Mechanics Department(机械工程与力学系)

专题命中 逻辑推理 :planning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00372 2025-08-15 cs.CV 78%

NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning

Zhixi Cai, Fucai Ke, Simindokht Jahangard, Maria Garcia de la Banda, Reza Haffari, Peter J. Stuckey, Hamid Rezatofighi

机构 * Monash University(莫纳什大学)

专题命中 逻辑推理 :reasoning(title,abstract)

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.04068 2025-05-09 cs.NI eess.SP 78%

Shadow Wireless Intelligence: Large Language Model-Driven Reasoning in Covert Communications

Yuanai Xie, Zhaozhi Liu, Xiao Zhang, Shihua Zhang, Rui Hou, Minrui Xu, Ruichen Zhang, Dusit Niyato

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11785 2025-05-01 cs.LO cs.MA 78%

Changing the Rules of the Game: Reasoning about Dynamic Phenomena in Multi-Agent Systems

Rustam Galimullin, Maksim Gladyshev, Munyque Mittelmann, Nima Motamed

专题命中 逻辑推理 :reasoning(title,abstract)

Comments Extended version of the AAMAS 2025 paper of the same name. In this version, proof of Theorem 4.1 is corrected, and all new text is in blue. We want to thank Stéphane Demri for spotting the problem

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15932 2025-04-23 cs.CV 78%

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning

Wang Lin, Liyu Jia, Wentao Hu, Kaihang Pan, Zhongqi Yue, Wei Zhao, Jingyuan Chen, Fei Wu, Hanwang Zhang

机构 * Zhejiang University(浙江大学) Nanyang Technological University(南洋理工大学) Huawei Singapore Research Center(华为新加坡研究中心)

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09258 2025-04-21 cs.CV cs.MM 78%

PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks

Jianyu Wu, Hao Yang, Xinhua Zeng, Guibing He, Zhiyu Chen, Zihui Li, Xiaochuan Zhang, Yangyang Ma, Run Fang, Yang Liu

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.10241 2025-03-14 cs.MA cs.HC cs.RO 78%

SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning

Dimitri Ognibene, Sabrina Patania, Luca Annese, Cansu Koyuturk, Franca Garzotto, Giuseppe Vizzari, Azzurra Ruggeri, Simone Colombani

专题命中 逻辑推理 :reasoning(title,abstract)

Comments 5 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.14688 2024-12-20 cs.IT math.IT 78%

Logic Induced High-Order Reasoning Network for Event-Event Relation Extraction

Peixin Huang, Xiang Zhao, Minghao Hu, Zhen Tan, Weidong Xiao

专题命中 逻辑推理 :reasoning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.06509 2024-12-13 cs.LO cs.FL cs.GT 78%

Reasoning about Strategic Abilities in Stochastic Multi-agent Systems

Yedi Zhang, Fu Song, Taolue Chen, Xuzhi Wu

专题命中 逻辑推理 :reasoning(title,abstract)

Comments Correction required and the replacement version not available shortly

详情

展开后加载摘要…

URL PDF HTML 收藏