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。

2025-08-06 至 2025-08-06 共收录 9 信号源:cs.CL, cs.AI, cs.LG

1. 规划推理 9 篇

2508.02956 2025-08-06 cond-mat.mtrl-sci cond-mat.dis-nn cond-mat.mes-hall cs.AI cs.LG 81%

Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoning

Alireza Ghafarollahi, Markus J. Buehler

机构 * Laboratory for Atomistic and Molecular Mechanics (LAMM) Massachusetts Institute of Technology(原子与分子力学实验室(LAMM)麻省理工学院) Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology(计算科学与工程中心施瓦茨曼计算学院麻省理工学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02789 2025-08-06 cs.AI 79%

Cognitive Loop via In-Situ Optimization: Self-Adaptive Reasoning for Science

Newman Cheng, Gordon Broadbent, William Chappell

机构 * Microsoft Discovery and Quantum, Office of the Chief Technology Officer(微软发现与量子,首席技术官办公室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03232 2025-08-06 cs.RO 78%

CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios

Muzhen Cai, Xiubo Chen, Yining An, Jiaxin Zhang, Xuesong Wang, Wang Xu, Weinan Zhang, Ting Liu

专题命中 规划推理 :planning(title,abstract)

Comments 9 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02999 2025-08-06 cs.AI cs.CL 73%

AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots

Xinjie Zhao, Moritz Blum, Fan Gao, Yingjian Chen, Boming Yang, Luis Marquez-Carpintero, Mónica Pina-Navarro, Yanran Fu, So Morikawa, Yusuke Iwasawa, Yutaka Matsuo, Chanjun Park, Irene Li

机构 * The University of Tokyo(东京大学) University of Bielefeld(比勒菲尔德大学) University of Alicante(阿利坎特大学) Soongsil University(顺世大学)

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

Comments CIKM 2025, Demo Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02962 2025-08-06 cs.RO 67%

Robot builds a robot's brain: AI generated drone command and control station hosted in the sky

Peter Burke

机构 * Department of Electrical Engineering and Computer Science, University of California, Irvine(电气工程与计算机科学系,加州大学伊文斯顿分校)

专题命中 规划推理 :reasoning(abstract);planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02711 2025-08-06 cs.LG cs.AI 62%

A Bayesian Hybrid Parameter-Efficient Fine-Tuning Method for Large Language Models

Yidong Chai, Yang Liu, Yonghang Zhou, Jiaheng Xie, Daniel Dajun Zeng

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23095 2025-08-06 cs.CL cs.AI 62%

SMART-Editor: A Multi-Agent Framework for Human-Like Design Editing with Structural Integrity

Ishani Mondal, Meera Bharadwaj, Ayush Roy, Aparna Garimella, Jordan Lee Boyd-Graber

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

Comments This requires some internal approval before the public release

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01056 2025-08-06 cs.ET cs.AI 57%

Managing Escalation in Off-the-Shelf Large Language Models

Sebastian Elbaum, Jonathan Panter

机构 * Council on Foreign Relations and University of Virginia(美国对外关系委员会和弗吉尼亚大学) Council on Foreign Relations(美国对外关系委员会)

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
2508.03345 2025-08-06 cs.AI 57%

Adaptive AI Agent Placement and Migration in Edge Intelligence Systems

Xingdan Wang, Jiayi He, Zhiqing Tang, Jianxiong Guo, Jiong Lou, Liping Qian, Tian Wang, Weijia Jia

机构 * Institute of Artificial Intelligence and Future Networks, Beijing Normal University, China(人工智能与未来网络研究院,北京师范大学,中国) Faculty of Arts and Sciences, Beijing Normal University, China(文理学院,北京师范大学,中国) Department of Computer Science and Engineering, Shanghai Jiao Tong University, China(计算机科学与工程系,上海交通大学,中国) College of Information Engineering, Zhejiang University of Technology, China(信息工程学院,浙江工业大学,中国)

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