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 4971 信号源:cs.CL, cs.AI, cs.LG

1. 复杂问题求解 4971 篇

2605.26520 2026-05-27 cs.CV cs.AI 90%

InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward

InterSketch: 一种具有自校正视觉草图和逐步奖励的交错推理模型

Zhiwei Ning, Wenwen Tong, Xiangli Kong, Shengnan Ma, Ziyi Shang, Jingcheng Ni, Tao Hu, Yong Xien Chng, Jixuan Ying, Zehuan Wu, Hanming Deng, Jie Yang, Yuanjie Zheng, Wei Liu, Lewei Lu

机构 * Shanghai Jiao Tong University(上海交通大学) SenseTime Research(商汤科技研究院) Shandong Normal University(山东师范大学)

专题命中 复杂问题求解 :reasoning(title,abstract);CoT(abstract,abstract_cn);chain-of-thought(abstract);logical reasoning(abstract)

AI总结 针对视觉-语言模型在长程视觉推理中文本中心范式局限性的问题,提出InterSketch模型,通过自校正和逐步奖励机制增强交错视觉-文本思维链能力,在视觉推理基准上超越Gemini-3-Pro等专有模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19281 2026-03-13 cs.AI 90%

Limited Reasoning Space: The cage of long-horizon reasoning in LLMs

有限推理空间:LLMs中长视图推理的牢笼

Zhenyu Li, Guanlin Wu, Cheems Wang, Yongqiang Zhao

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(abstract);CoT(abstract);planning(abstract)

AI总结 本文提出Halo框架,通过熵驱动的双控制器实现可控推理,解决LLM长视图任务中的推理限制问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.14114 2026-07-17 cs.CL cs.AI 新提交 90%

CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning

CoEvoT:用于图语言模型推理的协同进化思维链提示

Haohua Niu, Xingtong Yu, Yang Liu, Junfeng Fang, Xuanting Xie, Jie Tan, Zhongjian Zhang, Hong Cheng, Yuan Fang

机构 * Sun Yat-Sen University(中山大学) The Chinese University of Hong Kong(香港中文大学) Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所) National University of Singapore(新加坡国立大学) University of Electronic Science and Technology of China(电子科技大学) Beijing University of Posts and Telecommunieations(北京邮电大学) Singapore Management University(新加坡管理大学)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

AI总结 研究分布转移下的图学习问题,提出CoEvoT框架,通过文本到图令牌重写与图到文本推理指导的闭环协同进化,实现逐步的、状态感知的证据细化,在八个数据集实验中性能优于现有基准模型。

Comments Under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21724 2026-06-23 cs.CL cs.AI 新提交 90%

Denoising Iterative Self-Correction: Structured Verification Loops for Reliable LLM Reasoning

去噪迭代自校正:用于可靠LLM推理的结构化验证循环

Shen Yin, David Ken, Joel Stremmel

机构 * Thomson Reuters Labs(汤森路透实验室)

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

AI总结 提出DISC方法,通过将验证输出视为噪声测量,在多次验证-判断-校正循环中逐步减少推理错误,并引入二元判断门控机制防止破坏正确答案,在三个基准上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05355 2026-04-08 cs.AI cs.CL 90%

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

ETR:熵趋势奖励用于高效推理链推理

Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao Yu, Yang Wang

机构 * University of Toronto(多伦多大学) McMaster University(麦克马斯特大学) Concordia University(康考迪亚大学) University of Ottawa(渥太华大学)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

AI总结 本文提出ETR,通过轨迹感知的目标促进逐步不确定性降低,提升推理效率与准确性,实验表明在多个基准上显著提升性能。

Comments ACL 2026 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18956 2026-02-17 cs.AI cs.LG 90%

Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection

训练多模态大推理模型需要更优质的思考:一种用于长链式思考合成与选择的三阶段框架

Yizhi Wang, Linan Yue, Min-Ling Zhang

机构 * School of Computer Science and Engineering(计算机科学与工程学院) Key Laboratory of Computer Network and Information Integration (SEU), Ministry of Education(计算机网络与信息集成重点实验室(SEU))

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.AI、cs.LG

AI总结 本文提出SynSelect框架,通过三阶段合成与选择生成高质量多模态推理数据,提升模型推理能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00190 2026-01-30 cs.CL cs.AI 90%

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

可解释的链式思维推理:对状态感知推理动态的实证分析

Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li, Tong Yu, Xiang Chen, Ritwik Sinha, Jingbo Shang, Julian McAuley

机构 * University of California San Diego(加州大学圣地亚哥分校) Adobe Research(Adobe研究)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

AI总结 本文提出了一种状态感知的转换框架,通过结构化潜在动态分析链式思维推理的语义演变和转换,提升推理过程的可解释性。

Comments 5 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03140 2026-01-21 cs.CL cs.AI 90%

RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior

RCP-Merging: 通过将推理能力作为先验来融合长链式思维模型与领域特定模型

Junyao Yang, Jianwei Wang, Huiping Zhuang, Cen Chen, Ziqian Zeng

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

AI总结 RCP-Merging通过将推理能力作为先验,融合长链式思维模型与领域特定模型,提升领域任务性能9.5%-9.2%的同时保持原始推理能力。

Comments 15 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08058 2026-01-14 cs.CL cs.AI 90%

Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models

超越链式推理:大型语言模型中的一个潜在计算模式

Zhenghao He, Guangzhi Xiong, Bohan Liu, Sanchit Sinha, Aidong Zhang

机构 * University of Virginia(弗吉尼亚大学)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

AI总结 研究发现大型语言模型中的推理能力由潜在内部激活支持,通过引导特定潜在特征可提升性能,CoT提示并非唯一触发方式。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06002 2026-01-14 cs.CL cs.AI 90%

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

思维的分子结构:映射长链推理的拓扑结构

Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu, Songyao Duan, Jiarui Guo, Minghao Liu, Jiaheng Liu, Tong Yang, Ge Zhang, Libo Qin, Wanxiang Che, Wenhao Huang

机构 * LARG, SCIR, Harbin Institute of Technology(LARG、SCIR、哈尔滨工业大学) Peking University(北京大学) Nanjing University(南京大学) Central South University(中南大学)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

AI总结 本文提出通过分子结构类比理解长链推理的拓扑特性,引入有效语义异构体概念,并提出Mole-Syn方法提升长链推理性能和稳定性。

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03159 2025-11-06 cs.LG cs.AI 90%

CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

Jueon Park, Yein Park, Minju Song, Soyon Park, Donghyeon Lee, Seungheun Baek, Jaewoo Kang

机构 * Department of Computer Science and Engineering(计算机科学与工程系) AIGEN Sciences(AIGEN公司)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.AI、cs.LG

Comments Accepted to IEEE BIBM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01633 2025-11-04 cs.LG cs.AI 90%

Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving

Chengying Huan, Ziheng Meng, Yongchao Liu, Zhengyi Yang, Yun Zhu, Yue Yun, Shipeng Li, Rong Gu, Xiabao Wu, Haitao Zhang, Chuntao Hong, Shaonan Ma, Guihai Chen, Chen Tian

机构 * Nanjing University(南京大学) Ant Group(蚂蚁集团) University of New South Wales(新南威尔士大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Tsinghua University(清华大学)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.13534 2025-09-11 cs.CL cs.AI 90%

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models

Feiyang Li, Peng Fang, Zhan Shi, Arijit Khan, Fang Wang, Weihao Wang, Xin Zhang, Yongjian Cui

机构 * School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China(华中科技大学计算机科学与技术学院) Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China(华中科技大学光电实验室) Department of Computer Science, Bowling Green State University, Ohio, USA(Bowling Green State University 计算机科学系) Department of Computer Science, Aalborg University, Aalborg, Denmark(Aalborg University 计算机科学系) Huawei Technologies Co., Ltd, Shenzhen, China(华为技术有限公司)

专题命中 复杂问题求解 :reasoning(title,abstract);CoT(title,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
2508.02037 2025-08-22 cs.CL cs.AI 90%

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time

Huihan Li, You Chen, Siyuan Wang, Yixin He, Ninareh Mehrabi, Rahul Gupta, Xiang Ren

机构 * University of Southern California(南加州大学) University of California, San Diego(加州大学圣地亚哥分校) Meta Amazon AGI(亚马逊人工智能研究院)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.04684 2025-06-23 cs.CL cs.AI 90%

LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning

Zifan Xu, Haozhu Wang, Dmitriy Bespalov, Xian Wu, Peter Stone, Yanjun Qi

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) Amazon Web Service(亚马逊网络服务) Sony AI(索尼人工智能)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

Journal ref Findings of Empirical Methods in Natural Language Processing 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15894 2025-06-23 cs.CL cs.AI 90%

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning

Sam Silver, Jimin Sun, Ivan Zhang, Sara Hooker, Eddie Kim

机构 * Sam Silver(未知)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13307 2025-05-20 cs.CL cs.AI cs.CV 90%

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning

Qiguang Chen, Libo Qin, Jinhao Liu, Yue Liao, Jiaqi Wang, Jingxuan Zhou, Wanxiang Che

机构 * Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology(社会计算与交互机器人研究中心,哈尔滨工业大学) Faculty of Computing, Harbin Institute of Technology(计算学院,哈尔滨工业大学) School of Computer Science and Engineering, Central South University(计算机科学与工程学院,中南大学) Chinese University of Hong Kong(香港中文大学) MMLab, The Chinese University of Hong Kong(香港中文大学MMLab)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

Comments Manuscript

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14521 2025-03-20 cs.CY cs.AI cs.CL 90%

Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models

Yihang Chen, Haikang Deng, Kaiqiao Han, Qingyue Zhao

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.04537 2024-12-09 cs.CL cs.LG 90%

Understanding Hidden Computations in Chain-of-Thought Reasoning

Aryasomayajula Ram Bharadwaj

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.03271 2024-09-06 cs.AI cs.CL cs.HC 90%

Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation

Yu Wang, Shiwan Zhao, Zhihu Wang, Heyuan Huang, Ming Fan, Yubo Zhang, Zhixing Wang, Haijun Wang, Ting Liu

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.00923 2024-05-21 cs.CL cs.AI cs.CV 90%

Multimodal Chain-of-Thought Reasoning in Language Models

Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, Alex Smola

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

Comments Published in Transactions on Machine Learning Research

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.11797 2023-11-21 cs.CL cs.AI cs.CV cs.HC cs.MA 90%

Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents

Zhuosheng Zhang, Yao Yao, Aston Zhang, Xiangru Tang, Xinbei Ma, Zhiwei He, Yiming Wang, Mark Gerstein, Rui Wang, Gongshen Liu, Hai Zhao

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.14623 2023-10-24 cs.CL cs.LG 90%

CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks

Hoang H. Nguyen, Ye Liu, Chenwei Zhang, Tao Zhang, Philip S. Yu

专题命中 复杂问题求解 :chain-of-thought(title,abstract);CoT(title,abstract);reasoning(abstract);分类 cs.CL、cs.LG

Comments Accepted at EMNLP 2023 (Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04654 2025-11-07 cs.CL 90%

Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning

Mohammad Atif Quamar, Mohammad Areeb

机构 * Purdue University(普渡大学)

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

Comments Presented at the 1st Workshop on Efficient Reasoning (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.08693 2025-03-10 cs.RO cs.LG 90%

Robotic Control via Embodied Chain-of-Thought Reasoning

Michał Zawalski, William Chen, Karl Pertsch, Oier Mees, Chelsea Finn, Sergey Levine

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract,comments);分类 cs.LG

Comments Project Website: https://embodied-cot.github.io. Updated funding information

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.06060 2026-08-07 cs.CV 新提交 89%

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval

从失败中学习:基于难负例的以检索为中心的思维链用于统一多模态检索

Zelong Sun, Jun Wang, Kaicheng Yang, Tiancheng Gu, Ziyong Feng, Zhiwu Lu

专题命中 复杂问题求解 :CoT(title,summary_cn);reasoning(abstract);chain-of-thought(abstract)

AI总结 该研究提出UniME-R1框架,通过基于难负例的以检索为中心的思维链(RC-CoT)学习从检索失败中优化,在多模态检索基准上提升了性能。

Comments 26 pages,10 figures,14 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05746 2026-05-20 cs.AI cs.CL cs.LG 89%

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems

ARM:为通用多智能体系统发现代理推理模块

Bohan Yao, Shiva Krishna Reddy Malay, Vikas Yadav

机构 * University of Washington(华盛顿大学)

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

AI总结 本文提出了一种新的自动多智能体系统设计范式,通过优化链式推理(CoT)来发现代理推理模块(ARM),该模块通过在代码空间中进行树搜索,利用执行轨迹的反思来进化,从而提升多智能体系统的泛化能力。

Comments 29 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02178 2026-06-30 cs.AI 89%

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning

重新审视过度思考:在CoT推理中惩罚内部和外部冗余

Taihang Zhen, Jialiang Hong, Kai Chen, Guang Yang, Junlan Feng, Wenpeng Zhu, Jing Huo, Yang Gao, Depeng Wang, Haitao Wan, Xi Yang, Fanyu Meng, Yuyao Zhang, Ji Qi, Xiangyu Zhou

机构 * Nanjing University(南京大学)

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

AI总结 本文从语义效率角度重新审视过度思考问题,将CoT冗余分为内部和外部两种类型,并提出双惩罚强化学习框架以优化推理过程和终止行为,实验表明该方法在不同模型规模上显著减少推理长度并保持高精度。

Comments This work has been submitted to the IEEE for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05643 2026-04-15 cs.CL 89%

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs

基于图的链式推理剪枝:减少推理LLM中冗余反射

Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li

机构 * School of Geosciences and Info-Physics, Central South University(地质科学与信息物理学院,中南大学) Baidu Inc.(百度公司)

专题命中 复杂问题求解 :reasoning(title,abstract);chain-of-thought(title);CoT(abstract,abstract_cn);分类 cs.CL

AI总结 本文提出基于图的链式推理优化框架,通过剪枝策略减少推理过程中冗余反射,提升效率与准确性。

Comments Accepted by ACL2026 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01116 2026-03-17 cs.LG 89%

Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning

通过强化学习激发时间序列分析的链式推理

Felix Parker, Nimeesha Chan, Chi Zhang, Kimia Ghobadi

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

AI总结 本文提出COUNTS框架,通过强化学习训练LLM进行时间序列任务的链式推理,提升复杂时间数据处理能力。

详情

展开后加载摘要…

URL PDF HTML 收藏