The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification
LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence
Logit-Boundary Geometric Belief Interfaces and Sparse Sheaf-Enclave Protocols: A Self-Contained Substrate for Secure Network Electronic Health Record (EHR) Interoperability
机构
*
Department of Mechanical Engineering, University of Michigan, Ann Arbor, Michigan, USA(机械工程系,密歇根大学,安阿伯,密歇根州,美国)
;
Max-Planck-Institute for Sustainable Materials, Materials Informatics, Düsseldorf, Germany(可持续材料研究所,材料信息学,杜塞尔多夫,德国)
;
Mechanical Engineering, University of Michigan, Ann Arbor, Michigan, USA(机械工程,密歇根大学,安阿伯,密歇根州,美国)
CommentsPreprint. 16 pages, 2 figures. Live interactive demo: https://huggingface.co/spaces/Squagghy/moxia. Paper artifact and dataset on Zenodo (concept-DOI): 10.5281/zenodo.21906509
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI
具身融合智能体:以人为中心的智能体人工智能新范式
Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Yao, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang, Lei Li, Jiadong Guo, Minheng Ni, Weicong Lin, Chenxi Yang, Hongxiang Gao, Zhenghua Chen, Yang Bai, Min Wu, Jun Cheng, Huazhu Fu, Dacheng Tao, Bang Liu
机构
*
Université de Montréal(蒙特利尔大学)
;
Mila – Quebec Artificial Intelligence Institute(米拉-魁北克人工智能研究所)
;
Institute of Advanced Intelligence and Computing (IAIC), A*STAR(新加坡科技研究局高级智能与计算研究所)
;
Nanjing Medical University(南京医科大学)
;
Nanjing University(南京大学)
;
Renmin University of China(中国人民大学)
;
University of Cambridge(剑桥大学)
;
University of Oxford(牛津大学)
;
Tsinghua University(清华大学)
;
National University of Singapore(新加坡国立大学)
;
The Hong Kong University of Science and Technology(香港科技大学)
;
The Hong Kong Polytechnic University(香港理工大学)
;
Southern University of Science and Technology(南方科技大学)
;
Southeast University(东南大学)
;
University of Glasgow(格拉斯哥大学)
;
Nanyang Technological University(南洋理工大学)
专题命中
安全评测
:safety(abstract);分类 cs.AI
AI总结
该研究提出以人为中心的 Combodied Agents 新范式,整合多类智能体能力形成闭环,聚焦人类状态轨迹建模,推动智能体 AI 从任务完成转向人类持续福祉。
CommentsAn earlier version of this manuscript will appear in the proceedings of IEEE Cyber-AI 2026 Conference. Project source code is available at https://github.com/Keysight/LLM-EncodeGuard