arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Tencent(腾讯)

2026-07-14 至 2026-07-14 共收录 5
2607.08964 2026-07-14 cs.AI 版本更新

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

长视野终端基准测试:使用基于密集奖励的评分方式测试智能体在长视野终端任务中的极限

Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ninghao Liu, Lichao Sun, Haotao Mi, Leowei Liang

机构 * Tencent(腾讯) University of Maryland, College Park(马里兰大学帕克分校) University of Georgia(佐治亚大学) University of Minnesota, Twin Cities(明尼苏达大学双城分校) Indiana University(印第安纳大学) Lehigh University(里海大学) National University of Singapore(新加坡国立大学) The Hong Kong Polytechnic University(香港理工大学)

AI总结 研究针对现有终端基准测试局限,引入长视野终端基准测试(Long-Horizon-Terminal-Bench),含46个长视野任务。通过分解为分级子任务提供密集中间奖励,评估15个前沿模型,揭示改进空间,分析失败模式,发布该基准测试助力长视野终端智能体发展。

Comments 17 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.31651 2026-07-14 cs.AI 版本更新

FARS: A Fully Automated Research System Deployed at Scale

FARS:一个大规模部署的全自动研究系统

Qiong Tang, Tianxiang Sun, Xiangkun Hu, Xiangyang Liu, Yiran Chen, Yunfan Shao, Bobo Li, Changze Lv, Cheng Xu, Chengsong Huang, Chunyang Li, Dizhan Xue, Hao Bai, Haodong Duan, Hengquan Guo, Hongyang He, Hongyi Chen, Hui Shen, Jiahao Yuan, Jiankai Sun, Jikang Cheng, Jinfeng Xu, Jingqi Tong, Jingye Chen, Jinxiu Liu, Jixuan Leng, Junchi Yu, Kaixun Jiang, Kun Xiang, Kunpeng Yao, Lang Feng, Liangqi Yuan, Longsen Gao, Meng Li, Qi Jia, Qiushi Sun, Shengyuan Ding, Shizhan Gong, Siru Zhong, Terry Jingchen Zhang, Tianle Gu, Tianyi Liang, Weijie Liu, Weikai Yang, Weizhi Fei, Xin Wang, Xinpeng Liu, Xuanwen Ding, Yihong Tang, Yuanli Wang, Yukun Jiang, Yuming Yang, Zhengbao He, Zhikai Chen, Zhikun Xu, Zhuang Li, Zihao Huang

机构 * Analemma National University of Singapore(新加坡国立大学) Fudan University(复旦大学) University College Dublin(都柏林大学) Washington University in St. Louis(圣路易斯华盛顿大学) The Hong Kong University of Science and Technology(香港科技大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) ByteDance(字节跳动) ShanghaiTech University(上海科技大学) University of Warwick(华威大学) Carnegie Mellon University(卡内基梅隆大学) University of Michigan, Ann Arbor(密歇根大学安娜堡分校) East China Normal University(华东师范大学) Stanford University(斯坦福大学) Tencent(腾讯) The University of Hong Kong(香港大学) Shanghai Innovation Institute(上海创新研究院) Nex-AGI Team(Nex-AGI团队)

AI总结 提出FARS系统,通过分阶段智能体协作自动生成研究项目,在67个AI/ML主题上产出166篇论文,经282份评审验证其可产出有价值成果,同时暴露实验范围窄、方法局限和诚信问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.26795 2026-07-14 cs.CV cs.AI cs.MM 版本更新

NaviCache: Test-Time Self-Calibration Caching for Video Generation

NaviCache: 视频生成的测试时自校准缓存

Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang, Zhengyu Chen, Chengxi Zang, Zhou Zhao, Fei Wu

机构 * Zhejiang University(浙江大学) Cornell University(康奈尔大学) Tencent Hunyuan(腾讯文生视频)

AI总结 针对视频扩散模型计算成本高的问题,提出NaviCache方法,将特征演化重构思为惯性导航系统问题,通过双状态估计架构自适应跟踪特征变化比和潜在漂移,实现有界误差的计算跳过,在多个模型上取得优异性能。

Comments Published at ICML 2026: Proceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.11324 2026-07-14 cs.RO cs.AI cs.LG 版本更新

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Embodied-R1.5:通过具身基础模型演化物理智能

Yifu Yuan, Yaoting Huang, Xianze Yao, Yutong Li, Shuoheng Zhang, Linqi Han, Pengyi Li, Jiangeng Sun, Wenting Jia, Zhao Zhang, Yuhao Liu, Ruihao Liao, Yucheng Hu, Qiyu Wu, Yuxiao Li, Zibin Dong, Fei Ni, Yan Zheng, Shuyang Gu, Yi Ma, Hongyao Tang, Han Hu, Jianye Hao

机构 * Tianjin University(天津大学) Tencent Hunyuan(腾讯混元)

AI总结 提出统一具身基础模型Embodied-R1.5,通过自动化数据管道和多任务平衡强化学习,在8B参数下实现24项基准中16项最优,并支持微调为VLA模型。

Comments Embodied R1.5 technical report. Project page: https://embodied-r.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.03430 2026-07-14 cs.RO 版本更新

ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response

ProAct:用于结构感知主动响应的基准和多模态框架

Xiaomeng Zhu, Fengming Zhu, Weijie Zhou, Ye Tian, Zhenlin Hu, Yufei Huang, Yuchun Guo, Xinyu Wu, Zhengyou Zhang, Fangzhen Lin, Xuantang Xiong

机构 * Department of Computer Science and Engineering, The Hong Kong University of Science and Technology (HKUST), Hong Kong SAR, China(香港科技大学计算机科学与工程系) Tencent, Shenzhen, China(腾讯(中国深圳)) Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China(深圳先进技术研究所(SIAT),中国科学院)

AI总结 针对主动智能体开发受资源缺乏阻碍的问题,引入ProAct-75基准,提出由多模态大语言模型驱动的ProAct-Helper,其利用任务图进行行动选择,实验证明该方法在触发检测等方面优于闭源模型。

详情

展开后加载摘要…

URL PDF HTML 收藏