AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang, Peng Wang, Guan-Lin Chen, Yuejin Xie, Qinghua Mao, Wanying Qu, Yanxu Zhu, Tianyi Zhou, Lei Yuan, Zhijie Zheng, Qihao Lin, Yiming Wang, Haoyu Luo, Shuai Shao, Chen Qian, Qingyu Liu, Ling Tang, Ruiyang Qin, Qihan Ren, Junxiao Yang, Kun Wang, Zhiheng Xi, Linfeng Zhang, Ranjie Duan, Bo Zhang, Wenjie Wang, Wen Shen, Qiaosheng Zhang, Y. Teng, Chaochao Lu, Rui Mei, Man Li, Jialing Tao, Xi Lin, Tianhang Zheng, Yong Liu, Quanshi Zhang, Lei Zhu, Xingjun Ma, Junhua Liu, Hui Xue, X.Z. Zuo, Xiangnan He, Chaoyi Shen, Xianglong Liu, Min Huang, Jing Shao, Xia Hu
Abstract
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex a
Categories
Cite
@misc{liu2026agentdogb,
title = {{AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security}},
author = {Dongrui Liu and Yu Li and Zhonghao Yang and Peng Wang and Guan-Lin Chen and Yuejin Xie and Qinghua Mao and Wanying Qu and Yanxu Zhu and Tianyi Zhou and Lei Yuan and Zhijie Zheng and Qihao Lin and Yiming Wang and Haoyu Luo and Shuai Shao and Chen Qian and Qingyu Liu and Ling Tang and Ruiyang Qin and Qihan Ren and Junxiao Yang and Kun Wang and Zhiheng Xi and Linfeng Zhang and Ranjie Duan and Bo Zhang and Wenjie Wang and Wen Shen and Qiaosheng Zhang and Y. Teng and Chaochao Lu and Rui Mei and Man Li and Jialing Tao and Xi Lin and Tianhang Zheng and Yong Liu and Quanshi Zhang and Lei Zhu and Xingjun Ma and Junhua Liu and Hui Xue and X.Z. Zuo and Xiangnan He and Chaoyi Shen and Xianglong Liu and Min Huang and Jing Shao and Xia Hu},
year = {2026},
month = may,
eprint = {2605.29801},
archivePrefix = {arXiv},
url = {https://www.semanticscholar.org/paper/27d50468f1016b18c07283b56ea5dc0f5479b980}
}