机构
*
The Hong Kong Polytechnic University(香港理工大学)
;
The Hong Kong University of Science and Technology(香港科技大学)
;
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
通道卫士:安全模型无法组合成安全的多智能体系统
Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Tasfia Nuzhat Ornee, Maleeha Sheikh
机构
*
College of Engineering and Computer Science, University of Central Florida(工程与计算机科学学院,中央佛罗里达大学)
;
Department of Computer Science and Engineering, North South University(计算机科学与工程系,北南大学)
;
Computer Science and Engineering, Ahsanullah University of Science and Technology(计算机科学与工程,阿沙努拉科学与技术大学)
;
Department of Electrical and Computer Engineering, Purdue University Fort Wayne(电气与计算机工程系,普渡大学弗拉特沃恩分校)
When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
当置信度误导时:扩散语言模型的后缀锚定与锚邻近置信度调制
Jungwon Park, Jimyeong Kim, Jungmin Ko, Nojun Kwak, Wonjong Rhee
机构
*
RICS(智能研究学院)
;
AIIS(人工智能研究所)
;
IPAI(人工智能研究所)
;
Department of Intelligence and Information(智能与信息系)
;
Daegu Gyeongbuk Institute of Science and Technology(大邱庆州市科学技术院)
机构
*
Department of Computer Science\&Engineering, University of Minnesota-Twin Cities, Minnesota, USA
;
Department of Electrical Engineering, University of Minnesota-Twin Cities, Minnesota, USA
Comments17 pages, 3 figures, 6 tables (9-page main text). Ancillary file hidden-automata-rl-code.zip contains reproduction code and the complete per-run data behind every table and figure. v3: author name corrected, title revised, text rewritten for clarity, new robustness checks (nonlinear and off-policy probes) added; results and conclusions unchanged
机构
*
York University(约克大学)
;
Bangladesh University of Business and Technology(孟加拉国商业与技术大学)
;
RBC, Canada(加拿大RBC)
;
Nanyang Technological University(南洋理工大学)
;
Salesforce AI Research(Salesforce人工智能研究)
When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters
纠正特征何时有用?面向黑盒预测器的纠正特征发现智能体
Fangxin Wang, Ziyi Zhang, Diyi Zhuang, Langzhou He, Shiyu Wang, Baichuan Mo, Philip S. Yu
机构
*
University of Illinois Chicago(伊利诺伊大学芝加哥分校)
;
Texas A&M University(德克萨斯农工大学)
;
Massachusetts Institute of Technology(麻省理工学院)
;
Tsinghua University(清华大学)
Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent
觅食智能体中作为动态稳态优先级的内感受注意力
St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Bruce A. Bassett, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark Solms, Jonathan P. Shock
机构
*
Univ. of Cape Town(开普敦大学)
;
Neuroscience Institute, Univ. of Cape Town(开普敦大学神经科学研究所)
;
Laureate Institute for Brain Research(劳雷尔脑研究所)
;
University of the Witwatersrand(金山大学)
;
INRS(国家科学研究中心(加拿大))
;
Delft University of Technology(代尔夫特理工大学)
CommentsAccepted at SAB 2026 (From Animals to Animats 18), forthcoming in the Springer Lecture Notes in Artificial Intelligence proceedings. 20 pages, 11 numbered figures (12 graphics), 5 tables. The 12-page camera-ready paper is reproduced without alteration and followed by supplementary analyses that were not part of the proceedings paper. Code: https://github.com/sgrimbly/attention-aif-sab2026-snapshot