arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Tencent(腾讯)

2026-08-25 至 2026-08-25 共收录 3
2606.11119 2026-08-25 cs.LG cs.AI cs.CL 版本更新

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

TRACE:一种用于高效智能体强化学习的统一展开预算分配框架

Heming Zou, Qi Wang, Yun Qu, Yuhang Jiang, Lizhou Cai, Yixiu Mao, Ru Peng, Xin Xu, Weijie Liu, Kai Yang, Saiyong Yang, Xiangyang Ji

机构 * Tsinghua University(清华大学) Tencent(腾讯)

AI总结 针对多轮智能体强化学习中奖励对比度不足的问题,提出TRACE框架,通过将每个ReAct式思考-行动-观察步骤建模为语义节点,在固定采样预算内将预算分配到提示根和中间前缀,增强奖励对比,提升策略更新信号。

Comments Accepted by EMNLP 2026 Main Conference, 32 pages, 12 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.11421 2026-08-25 cs.CV 版本更新

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

ShotVerse: 提升文本驱动多镜头视频创作的电影级摄像机控制

Songlin Yang, Zhe Wang, Xuyi Yang, Songchun Zhang, Xianghao Kong, Taiyi Wu, Xiaotong Zhao, Ran Zhang, Alan Zhao, Anyi Rao

机构 * Tencent Video AI Center, PCG, Tencent(腾讯视频AI中心)

AI总结 ShotVerse通过'计划然后控制'框架,结合视觉语言模型和摄像机适配器,实现多镜头视频创作中精准的摄像机控制与高保真电影效果。

Comments SIGGRAPH Asia 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.04448 2026-08-25 cs.AI cs.CL cs.CV cs.LG cs.MA 版本更新

SkillNet: Create, Evaluate, and Connect AI Skills

SkillNet: 创建、评估和连接AI技能

Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Yida Xue, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen

机构 * Zhejiang University(浙江大学) Tongji University(同济大学) Southeast University(东南大学) Alibaba Group(阿里巴巴集团) Tencent(腾讯) Fudan University(复旦大学) The University of Edinburgh(爱丁堡大学) Monash University(墨尔本大学) National University of Singapore(新加坡国立大学) Nanyang Technological University(南洋理工大学) Huzhou University(湖州大学) Hornor Device Co., Ltd(Hornor设备有限公司) Hangzhou Institute for Advanced Study, UCAS(杭州先进研究所,UCAS)

AI总结 SkillNet通过统一的本体和多维评估机制,大规模创建、评估和连接AI技能,提升代理性能并促进技能的持久掌握。

Comments this http URL (http://skillnet.openkg.cn/;) add SkillNet-Gym, a benchmark for evaluating skill retrieval, utilization, composition, and SkillNet-Fabric for task-specific skill routing through lightweight Wikis

详情

展开后加载摘要…

URL PDF HTML 收藏