arXivDaily arXiv每日学术速递 周一至周五更新

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 5021 信号源:cs.CL, cs.AI, cs.LG

1. 复杂问题求解 5021 篇

2508.02841 2025-08-06 cs.AI cs.IR 79%

A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering

Ziruo Yi, Jinyu Liu, Ting Xiao, Mark V. Albert

机构 * University of North Texas(北卡罗来纳州立大学)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02150 2025-08-05 cs.AI 79%

Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following

Qingyu Ren, Qianyu He, Bowei Zhang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

机构 * Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University(上海数据科学关键实验室,计算机科学与人工智能学院,复旦大学) School of Data Science, Fudan University(数据科学学院,复旦大学) Ant Group(蚂蚁集团)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00323 2025-08-04 cs.AI 79%

Oedipus and the Sphinx: Benchmarking and Improving Visual Language Models for Complex Graphic Reasoning

Jianyi Zhang, Xu Ji, Ziyin Zhou, Yuchen Zhou, Shubo Shi, Haoyu Wu, Zhen Li, Shizhao Liu

机构 * Beijing Electronic Science & Technology Institute(北京电子科学技术研究所)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02467 2025-08-04 cs.AI 79%

BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking

Qisheng Hu, Quanyu Long, Wenya Wang

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

Comments Work in Progress

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.10009 2025-08-04 cs.AI math.OC 79%

OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

Bowen Zhang, Pengcheng Luo, Genke Yang, Boon-Hee Soong, Chau Yuen

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

Comments 8 pages, 13 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17699 2025-07-24 cs.AI 79%

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations

Zhao Song, Song Yue, Jiahao Zhang

机构 * University of California, Berkeley(加州大学伯克利分校) Northeastern University(东北大学) Large Reasoning Models (LRMs)(大型推理模型)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.14468 2025-07-23 cs.AI 79%

BioGraphFusion: Graph Knowledge Embedding for Biological Completion and Reasoning

Yitong Lin, Jiaying He, Jiahe Chen, Xinnan Zhu, Jianwei Zheng, Tao Bo

机构 * College of Computer Science Technology , Zhejiang University of Technology , Hangzhou , Zhejiang , 310023 , China Key Laboratory of Endocrine Glucose \& Lipids Metabolism , Department of Endocrinology, Shandong Provincial Hospital Affiliated to Shandong First Medical University , Jinan , Shandong , China

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

Comments Accepted by Bioinformatics on July 11th

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.09638 2025-07-15 cs.CL 79%

Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?

Pawitsapak Akarajaradwong, Chompakorn Chaksangchaichot, Pirat Pothavorn, Attapol Thamrongrattanarit-Rutherford, Ekapol Chuangsuwanich, Sarana Nutanong

机构 * VISAI AI(VISAI人工智能) Chulalongkorn University(朱拉隆功大学) Vidyasirimedhi Institute of Science and Technology(维达沙里梅迪科技研究院)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08046 2025-07-14 cs.AI 79%

TableReasoner: Advancing Table Reasoning Framework with Large Language Models

Sishi Xiong, Dakai Wang, Yu Zhao, Jie Zhang, Changzai Pan, Haowei He, Xiangyu Li, Wenhan Chang, Zhongjiang He, Shuangyong Song, Yongxiang Li

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.06013 2025-07-09 cs.AI 79%

CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation

Kushal Gajjar, Harshit Sikchi, Arpit Singh Gautam, Marc Hammons, Saurabh Jha

机构 * Dell Technologies(戴尔技术)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.09438 2025-07-02 physics.ed-ph cs.AI 79%

Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational Assessment

Paul Tschisgale, Holger Maus, Fabian Kieser, Ben Kroehs, Stefan Petersen, Peter Wulff

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18071 2025-06-30 cs.CV cs.AI 79%

MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering

Jisheng Dang, Huilin Song, Junbin Xiao, Bimei Wang, Han Peng, Haoxuan Li, Xun Yang, Meng Wang, Tat-Seng Chua

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21277 2025-06-27 cs.CV cs.CL 79%

HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context

Qize Yang, Shimin Yao, Weixuan Chen, Shenghao Fu, Detao Bai, Jiaxing Zhao, Boyuan Sun, Bowen Yin, Xihan Wei, Jingren Zhou

机构 * Tongyi Lab, Alibaba Group(通义实验室,阿里巴巴集团)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19492 2025-06-25 cs.CL 79%

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs

Shu Yang, Junchao Wu, Xuansheng Wu, Derek Wong, Ninhao Liu, Di Wang

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19095 2025-06-25 cs.AI 79%

Baba is LLM: Reasoning in a Game with Dynamic Rules

Fien van Wetten, Aske Plaat, Max van Duijn

机构 * LIACS, Leiden University, The Netherlands(LIACS,莱顿大学,荷兰)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17864 2025-06-24 cs.CL 79%

QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs

Taolin Zhang, Haidong Kang, Dongyang Li, Qizhou Chen, Chengyu Wang Xiaofeng He, Richang Hong

专题命中 复杂问题求解 :self-correction(title,abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17211 2025-06-23 cs.LG 79%

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

Xuechen Zhang, Zijian Huang, Yingcong Li, Chenshun Ni, Jiasi Chen, Samet Oymak

机构 * University of Michigan(密歇根大学)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14374 2025-06-18 cs.CR cs.LG 79%

Excessive Reasoning Attack on Reasoning LLMs

Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.11934 2025-06-17 cs.AI 79%

Stepwise Reasoning Error Disruption Attack of LLMs

Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu

机构 * University of Science and Technology of China(中国科学技术大学) City University of Hong Kong(香港城市大学) Independent Researcher(独立研究者)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.11600 2025-06-16 cs.IR cs.AI 79%

GraphRAG-Causal: A novel graph-augmented framework for causal reasoning and annotation in news

Abdul Haque, Umm e Hani, Ahmad Din, Muhammad Babar, Ali Abbas, Insaf Ullah

机构 * Dept. of Artificial Intelligence & Data Science FAST School of Computing NUCES(人工智能与数据科学系 FAST 计算学院 NUCES) Dept. of Computing and Electronics Engineering Middle East College(计算与电子工程系 中东学院) Institute for Analytics and Data Science University of Essex(分析与数据科学研究所 埃塞克斯大学)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

Comments 18 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.19164 2025-06-16 cs.AI cs.IR 79%

Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery

Sounak Lahiri, Sumit Pai, Tim Weninger, Sanmitra Bhattacharya

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

Comments Updated with Camera Ready Copy for ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07943 2025-06-12 cs.CV cs.AI 79%

Decoupling the Image Perception and Multimodal Reasoning for Reasoning Segmentation with Digital Twin Representations

Yizhen Li, Dell Zhang, Xuelong Li, Yiqing Shen

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

Comments This work was submitted without the consent of all co-authors. We request withdrawal until all parties agree

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09038 2025-06-11 cs.AI 79%

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions

Polina Kirichenko, Mark Ibrahim, Kamalika Chaudhuri, Samuel J. Bell

机构 * FAIR at Meta(Meta的FAIR)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.13540 2025-06-09 cs.CL cs.CV 79%

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning

Yingjie Zhu, Xuefeng Bai, Kehai Chen, Yang Xiang, Jun Yu, Min Zhang

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China(计算与智能研究院,哈尔滨工业大学,深圳) Peng Cheng Laboratory, Shenzhen, China(鹏城实验室,深圳) School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China(智能科学与工程学院,哈尔滨工业大学,深圳)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

Comments Accepted by ACL2025 main conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01970 2025-06-04 cs.LG cs.CV 79%

Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Ability

Ruizhuo Song, Beiming Yuan

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.LG

Comments 15 pages, 15 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01273 2025-06-03 cs.AI 79%

RAISE: Reasoning Agent for Interactive SQL Exploration

Fernando Granado, Roberto Lotufo, Jayr Pereira

机构 * Universidade Estadual de Campinas (UNICAMP)(坎皮纳斯州立大学(UNICAMP))

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01253 2025-06-03 cs.CL 79%

CoRE: Condition-based Reasoning for Identifying Outcome Variance in Complex Events

Sai Vallurupalli, Francis Ferraro

机构 * Department of Computer Science and Electrical Engineering University of Maryland, Baltimore County(计算机科学与电气工程系马里兰大学巴尔的摩县)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

Comments Accepted to Findings of the Association for Computational Linguistics 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01116 2025-06-03 cs.AI q-bio.QM 79%

ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation

Xinyi Liu, Lipeng Ma, Yixuan Li, Weidong Yang, Qingyuan Zhou, Jiayi Song, Shuhao Li, Ben Fei

机构 * Fudan University(复旦大学) The Chinese University of Hong Kong(香港中文大学)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09923 2025-06-03 cs.CL 79%

Guiding Reasoning in Small Language Models with LLM Assistance

Yujin Kim, Euiin Yi, Minu Kim, Se-Young Yun, Taehyeon Kim

机构 * KAIST AI(韩国科学技术院人工智能研究所) LG AI Research(LG人工智能研究院)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

Comments 20 pages, 12 figures, 9 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.16837 2025-06-03 cs.CL 79%

Do Large Language Models Latently Perform Multi-Hop Reasoning?

Sohee Yang, Elena Gribovskaya, Nora Kassner, Mor Geva, Sebastian Riedel

机构 * Google DeepMind(谷歌DeepMind) UCL(伦敦大学学院) Google Research(谷歌研究) Tel Aviv University(特拉维夫大学)

专题命中 复杂问题求解 :reasoning(title,abstract);分类 cs.CL

Comments ACL 2024

详情

展开后加载摘要…

URL PDF HTML 收藏