arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

2025-12-22 至 2025-12-22 共收录 5 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. GUI与网页智能体 5 篇

2511.22685 2025-12-22 cs.RO 75%

Deadlock-Free Hybrid RL-MAPF Framework for Zero-Shot Multi-Robot Navigation

无死锁的混合式RL-MAPF框架用于零样本多机器人导航

Haoyi Wang, Licheng Luo, Yiannis Kantaros, Bruno Sinopoli, Mingyu Cai

机构 * Department of Mechanical Engineering University of California Riverside CA USA(加州大学河滨分校机械工程系) Department of Electrical and Systems Engineering Washington University in St. Louis MO USA(华盛顿大学圣路易斯分校电气与系统工程系)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract)

AI总结 本文提出一种无死锁的混合RL-MAPF框架,通过整合反应性RL导航与按需MAPF干预,实现零样本多机器人导航的鲁棒性能。

Comments 18 pages (including appendix), 3 figures. Project page (videos, animations, additional resources): https://wanghaoyi518.github.io/rl-mapf-project-page/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17584 2025-12-22 cs.RO 50%

Optimized Scheduling and Positioning of Mobile Manipulators in Collaborative Applications

协作应用中移动机械臂的优化调度与定位

Christian Cella, Sole Ester Sonnino, Marco Faroni, Andrea Zanchettin, Paolo Rocco

机构 * Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria(米兰理工大学电子、信息与生物工程学院)

专题命中 GUI与网页智能体 :planning(abstract)

AI总结 本文提出基于数字模型的优化框架,用于协作环境中移动机械臂的调度与定位,通过PSO平衡KPIs,提升任务执行效率与适应性。

Comments Accepted at The IFAC Joint Conference on Computers, Cognition and Communication (J3C) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17553 2025-12-22 cs.RO 50%

Deep Learning-based Robust Autonomous Navigation of Aerial Robots in Dense Forests

基于深度学习的密集森林中无人机鲁棒自主导航

Guglielmo Del Col, Väinö Karjalainen, Teemu Hakala, Yibo Zhang, Eija Honkavaara

机构 * Department of Remote Sensing and Photogrammetry, Finnish Geospatial Research Institute FGI, The National Land Survey of Finland(遥感与摄影测量系,芬兰地理空间研究 institute FGI,芬兰国家土地测绘局)

专题命中 GUI与网页智能体 :planning(abstract)

AI总结 本文提出一种基于深度学习的无人机导航方法,通过改进的深度编码和神经运动原始评价,提高在密集森林中的自主导航能力,实验证明其在复杂环境中的可靠性和安全性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.15431 2025-12-22 cs.CV 50%

Step-GUI Technical Report

Step-GUI 技术报告

Haolong Yan, Jia Wang, Xin Huang, Yeqing Shen, Ziyang Meng, Zhimin Fan, Kaijun Tan, Jin Gao, Lieyu Shi, Mi Yang, Shiliang Yang, Zhirui Wang, Brian Li, Kang An, Chenyang Li, Lei Lei, Mengmeng Duan, Danxun Liang, Guodong Liu, Hang Cheng, Hao Wu, Jie Dong, Junhao Huang, Mei Chen, Renjie Yu, Shunshan Li, Xu Zhou, Yiting Dai, Yineng Deng, Yingdan Liang, Zelin Chen, Wen Sun, Chengxu Yan, Chunqin Xu, Dong Li, Fengqiong Xiao, Guanghao Fan, Guopeng Li, Guozhen Peng, Hongbing Li, Hang Li, Hongming Chen, Jingjing Xie, Jianyong Li, Jingyang Zhang, Jiaju Ren, Jiayu Yuan, Jianpeng Yin, Kai Cao, Liang Zhao, Liguo Tan, Liying Shi, Mengqiang Ren, Min Xu, Manjiao Liu, Mao Luo, Mingxin Wan, Na Wang, Nan Wu, Ning Wang, Peiyao Ma, Qingzhou Zhang, Qiao Wang, Qinlin Zeng, Qiong Gao, Qiongyao Li, Shangwu Zhong, Shuli Gao, Shaofan Liu, Shisi Gao, Shuang Luo, Xingbin Liu, Xiaojia Liu, Xiaojie Hou, Xin Liu, Xuanti Feng, Xuedan Cai, Xuan Wen, Xianwei Zhu, Xin Liang, Xin Liu, Xin Zhou, Yifan Sui, Yingxiu Zhao, Yukang Shi, Yunfang Xu, Yuqing Zeng, Yixun Zhang, Zejia Weng, Zhonghao Yan, Zhiguo Huang, Zhuoyu Wang, Zihan Yan, Zheng Ge, Jing Li, Yibo Zhu, Binxing Jiao, Xiangyu Zhang, Daxin Jiang

机构 * GELab-Team(GELab团队)

专题命中 GUI与网页智能体 :agent(abstract)

AI总结 Step-GUI 是一种先进的 GUI 代理,通过自我进化训练管道和 GUI-MCP 协议,在保持高准确率的同时实现高效隐私保护的 GUI 自动化。

Comments 41 pages, 26 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11011 2025-12-22 cs.RO 50%

Efficient Image-Goal Navigation with Representative Latent World Model

高效图像-目标导航与代表性潜在世界模型

Zhiwei Zhang, Hui Zhang, Kaihong Huang, Chenghao Shi, Huimin Lu

机构 * College of Intelligence Science and Technology, the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology(智能科学与技术学院、装备状态感知与智能支持国家重点实验室、国防科技大学)

专题命中 GUI与网页智能体 :planning(abstract)

AI总结 本文提出ReL-NWM模型,通过在高层次语义潜在空间中进行预测和规划,实现高效图像-目标导航。

详情

展开后加载摘要…

URL PDF HTML 收藏