AI Agent

Logical Robots: Declarative Multi-Agent Programming in Logica

逻辑机器人：逻辑编程中的多智能体编程

Evgeny Skvortsov, Yilin Xia, Ojaswa Garg, Shawn Bowers, Bertram Ludäscher

机构 * Google LLC（谷歌公司） ； University of Illinois（伊利诺伊大学） ； Gonzaga University（贡扎加大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.AI

AI总结 Logical Robots通过逻辑编程语言Logica实现多智能体仿真平台，将观察映射到动作输出，实现低层反应控制与高层规划的结合。

Comments International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 25-29, 2026. Paphos, Cyprus

CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences

CompanionCast：迈向多智能体系统在共享体验中的社会协作

Yiyang Wang, Chen Chen, Tica Lin, Vishnu Raj, Josh Kimball, Alex Cabral, Josiah Hester

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Dolby Laboratories, Inc.（杜比实验室） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；AI agent(abstract)；分类 cs.CL

AI总结 CompanionCast通过多智能体系统提升共享体验中的社会协作，通过多模态检测、上下文缓存和空间音频增强共在感，实验显示其在体育观看中显著提升社会存在感和情感共享。

Comments Accepted at ACM CHI 2026 Workshop on Human-Agent Collaboration

The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systems

在LLM多智能体系统中，社会学习和集体规范形成促进合作的作用

Prateek Gupta, Qiankun Zhong, Hiromu Yakura, Thomas Eisenmann, Iyad Rahwan

机构 * Center for Humans and Machines（人类与机器中心） ； Max-Planck Institute for Human Development（人类发展马克斯·普朗克研究所） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 本文提出了一种无显式奖励信号的CPR模拟框架，通过社会学习和规范惩罚机制研究LLM多智能体系统中合作与规范的内生形成。

Comments Accepted at the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)

Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models

多智能体AI工作流中的时间攻击模式检测：一种用于训练基于轨迹的安全模型的开放框架

Ron F. Del Rosario

机构 * SAP ； OWASP Gen AI Security Project（OWASP生成人工智能安全项目） ； Agentic Security Initiative (ASI)（代理安全倡议（ASI）） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract,comments)；分类 cs.AI

AI总结 本文提出了一种开放框架，通过合成轨迹生成和微调语言模型，提升多智能体AI工作流中时间攻击模式检测的准确性，并公开了相关数据集和评估基准。

Comments 26 pages, 3 figures, 7 tables. Datasets and code: https://huggingface.co/guerilla7/agentic-safety-gguf

A cybersecurity AI agent selection and decision support framework

Masike Malatji

专题命中 多智能体 ：AI agent(title,abstract)；agent(title,abstract)；multi-agent(abstract)；分类 cs.AI

Comments 6 figures, 6 tables, AI agents decision support framework

Factorised Active Inference for Strategic Multi-Agent Interactions

Jaime Ruiz-Serra, Patrick Sweeney, Michael S. Harré

机构 * Centre for Complex Systems, The University of Sydney（复杂系统中心，悉尼大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.LG

Comments To appear in Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2025). Detroit, USA, May 2025

Decentralized Multi-agent Plan Repair in Dynamic Environments

Antonín Komenda, Peter Novák, Michal Pěchouček

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.AI

Comments 21 pages, 5 algorithms, 3 figures. This is the full version of an extended abstract published in Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), Conitzer, Winikoff, Padgham, and van der Hoek (eds.), June, 4--8, 2012, Valencia, Spain

Kimi K2.5: Visual Agentic Intelligence

Kimi K2.5：视觉代理智能

Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S. H. Cai, Yuan Cao, Ziwei Chai, Y. Charles, H. S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Yean Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Hao Ding, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Angang Du, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yu Fan, Shengjun Fang, Qiulin Feng, Yichen Feng, Garimugai Fu, Kelin Fu, Hongcheng Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Qizheng Gu, Xinran Gu, Yicheng Gu, Longyu Guan, Shuhao Guan, Yuanying Guo, Xiaoru Hao, Dailan He, Tianhong He, Weiran He, Wenyang He, Yibo He, Yunjia He, Chao Hong, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Chaobo Jia, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guokun Lai, Aidi Li, C. Li, Cheng Li, Fang Li, Guanghe Li, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li, Yuxiao Li, Zhaowei Li, Zhaoxi Li, Zheming Li, Weilong Liao, Jiawei Lin, Xiaohan Lin, Yibo Lin, Zhishan Lin, Zichao Lin, Cheng Liu, Chenyu Liu, Hongzhang Liu, Liang Liu, Shaowei Liu, Shudong Liu, Shuran Liu, Tianwei Liu, Tianyu Liu, Weizhou Liu, Xiangyan Liu, Yangyang Liu, Yanming Liu, Yibo Liu, Yuanxin Liu, Zhengying Liu, Zhongnuo Liu, Enzhe Lu, Haoyu Lu, Zhiyuan Lu, G. Luo, Junyu Luo, Tongxu Luo, Yashuo Luo, Long Ma, Shaoguang Mao, Yuan Mei, Xin Men, Fanqing Meng, Zhiyong Meng, Yibo Miao, Minqing Ni, Kun Ouyang, Siyuan Pan, Bo Pang, Yuchao Qian, Ruoyu Qin, Zeyu Qin, Jiezhong Qiu, Bowen Qu, Zeyu Shang, Youbo Shao, Tianxiao Shen, Zhennan Shen, Juanfeng Shi, Lidong Shi, Shengyuan Shi, Feifan Song, Pengwei Song, Tianhui Song, Xiaoxi Song, Hongjin Su, Jianlin Su, Zhaochen Su, Lin Sui, Jinsong Sun, Junyao Sun, Tongyu Sun, Flood Sung, Yunpeng Tai, Chuning Tang, Heyi Tang, Xiaojuan Tang, Zhengyang Tang, Jiawen Tao, Shiyuan Teng, Chaoran Tian, Pengfei Tian, Bowen Wang, Chensi Wang, Chuang Wang, Congcong Wang, Dingkun Wang, Dinglu Wang, Dongliang Wang, Feng Wang, Hailong Wang, Haiming Wang, Hao Wang, Hengzhi Wang, Huaqing Wang, Hui Wang, Jiahao Wang, Jinhong Wang, Jiuzheng Wang, Kaixin Wang, Linian Wang, Qibin Wang, Shengjie Wang, Shuyi Wang, Si Wang, Wei Wang, Xiaochen Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yipu Wang, Yiqin Wang, Yucheng Wang, Yuzhi Wang, Zhaoji Wang, Zhaowei Wang, Zhengtao Wang, Zhexu Wang, Zifan Wang, Zihan Wang, Zizhe Wang, Chu Wei, Ming Wei, Chuan Wen, Zichen Wen, Chengjie Wu, Haoning Wu, Junyan Wu, Rucong Wu, Wenhao Wu, Yuefeng Wu, Yuhao Wu, Yuxin Wu, Zijian Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Yuchong Xie, Bowei Xing, Boyu Xu, Jianfan Xu, Jing Xu, Jinjing Xu, L. H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinbo Xu, Xinran Xu, Yangchuan Xu, Yichang Xu, Yuemeng Xu, Zelai Xu, Ziyao Xu, Junjie Yan, Yuzi Yan, Guangyao Yang, Hao Yang, Junwei Yang, Kai Yang, Ningyuan Yang, Xiaofei Yang, Xinlong Yang, Xinyu Yang, Ying Yang, Yi Yang, Yi Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Dan Ye, Haoran Ye, Wenjie Ye, Zhuorui Ye, Peng Yebo, Bohong Yin, Chengzhen Yu, Longhui Yu, Tao Yu, Tianxiang Yu, Enming Yuan, Mengjie Yuan, Xiaokun Yuan, Yang Yue, Weihao Zeng, Dunyuan Zha, Haobing Zhan, Dehao Zhang, Hao Zhang, Jin Zhang, Puqi Zhang, Qiao Zhang, Rui Zhang, Xiaobin Zhang, Xiaoyun Zhang, Y. Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yushun Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Chenguang Zhao, Feifan Zhao, Jinxiang Zhao, Shuai Zhao, Xiangyu Zhao, Xuanle Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Ruihan Zheng, Shaojie Zheng, Tengyang Zheng, Junfeng Zhong, Longguang Zhong, Weiming Zhong, M. Zhou, Runjie Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Liya Zhu, Xinhao Zhu, Yuxuan Zhu, Zhen Zhu, Jingze Zhuang, Weiyu Zhuang, Ying Zou, Xinxing Zu

机构 * Kimi Team（Kimi 团队） 纠错

专题命中 多智能体 ：agent(summary_cn,abstract)；agentic(title,abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结 Kimi K2.5通过联合优化文本和视觉模态，提出Agent Swarm框架，实现多模态代理智能的先进性能和高效任务处理。

Comments Kimi K2.5 tech report

Auditing Emergent LLM-Agent Collaboration through Cooperation-Obligation Coupling

通过合作-义务耦合对大语言模型智能体（LLM-agent）的涌现协作进行审计

Zuyuan Zhang, Hanqing Yang, Carlee Joe-Wong, Tian Lan

专题命中 多智能体 ：agent(title,title_cn)

AI总结 针对LLM-agent协作审计的可审计性缺口，本文提出iCORE表示方法，建立合作-义务耦合审计框架，实验验证其可准确检测缺陷并显著提升轨迹与终端性能。

Agent-OSI: An Interoperability Architecture for Communication and Settlement in the Decentralized Internet of Agents

Agent-OSI: 向去中心化的智能体互联网的分层协议栈

Wenxin Xu, Taotao Wang, Yihan Xia, Shengli Zhang, Soung Chang Liew

专题命中 多智能体 ：agent(title,title_cn)

AI总结 Agent-OSI提出了一种基于现有互联网的六层协议栈，旨在实现去中心化智能体网络的互操作性、信任和按使用付费结算。

Comments 8 pages, 3 figures

Multi-Agent Robotic Control with Onboard Vision-Language Models

基于机载视觉语言模型的多智能体机器人控制

Kajetan Rachwał, Maciej Majek, Bartłomiej Boczek, Jakub Matejczyk, Dominik Matejkowski, Adam Dąbrowski, Tim Seyde, Alexander Amini, Maria Ganzha

机构 * Faculty of Mathematics and Information Science, Warsaw University of Technology（华沙技术大学数学与信息科学学院） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

AI总结 研究针对视觉语言模型用于机器人控制的挑战，提出多智能体系统架构，在机载硬件部署智能体，用紧凑型VLMs并经微调及新型编排智能体，经硬件在环模拟验证，证明该机载架构可行高效，有实际应用潜力且模拟环境已开源。

Comments 6 pages, 2 figures, accepted to 24th International Conference on Practical applications of Agents and Multi-Agent Systems (PAAMS'26)

Envisioning Sensemaking in Multi-Human, Multi-Agent Collaborative Knowledge Work

设想多人类、多智能体协作知识工作中的意义建构

Zhitong Guan, Soo Young Rieh

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；AI agent(abstract)

AI总结 探讨生成式AI如何重塑协作知识工作中的意义建构，提出五项设计原则及一个动态共享表征工作空间框架，支持人类与AI代理共同构建可协商的知识。

Comments This is the Author's Accepted Manuscript version of the article: Guan, Z., \& Rieh, S. Y. (2026). Envisioning Sensemaking in Multi-Human, Multi-Agent Collaborative Knowledge Work. Accepted for publication in \textit{Sensemaking @ CHI 2026}

MAEBE: Multi-Agent Emergent Behavior Framework

Sinem Erisken, Timothy Gothard, Martin Leitgab, Ram Potham

机构 * Independent Researcher（独立研究者） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments Preprint. This work has been submitted to the Multi-Agent Systems Workshop at ICML 2025 for review

Asynchronous Spatial-Temporal Allocation for Trajectory Planning of Heterogeneous Multi-Agent Systems

Yuda Chen, Haoze Dong, Zhongkui Li

专题命中 多智能体 ：agent(title,abstract)；planning(title)；multi-agent(title)

Comments 8 pages

Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering

Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments A full version of the paper will be released soon. The codes are available at https://github.com/bowen-upenn/Multi-Agent-VQA

Pommerman: A Multi-Agent Playground

Cinjon Resnick, Wes Eldridge, David Ha, Denny Britz, Jakob Foerster, Julian Togelius, Kyunghyun Cho, Joan Bruna

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments Oral at the AIIDE Multi-Agent Workshop; 0xc8Ac61A4025B35e425b829fCFCab37f038993963

Modeling Communication of Collaborative Multi-Agent System under Epistemic Planning

Abeer Alshehri, Tim Miller, Liz Sonenberg

专题命中 多智能体 ：planning(title,abstract)；agent(title)；multi-agent(title)

Comments 19 pages, 6 figures, 4 tables Submitted to International Journal of Intelligent Systems

Journal ref Int J Intell Syst. 2021; 1- 22

Re-conceptualising the Language Game Paradigm in the Framework of Multi-Agent Reinforcement Learning

Paul Van Eecke, Katrien Beuls

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments This paper was accepted for presentation at the 2020 AAAI Spring Symposium `Challenges and Opportunities for Multi-Agent Reinforcement Learning' after a double-blind reviewing process

Multi-Agent System Interaction in Integrated SCM

Ritu Sindhu, Abdul Wahid, G. N. Purohit

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments International Journal of Computer Science Issues, IJCSI Volume 5, pp33-37, October 2009

Journal ref R. Sindhu, A. W. and G.N.Purohit, "Multi-Agent System Interaction in Integrated SCM", International Journal of Computer Science Issues, IJCSI, Volume 5, pp33-37, October 2009

Towards Participatory Design of Multi-agent Approach to Transport Demands

Yee Ming Chen, Bo-Yuan Wang

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments "International Journal of Computer Science Issues, IJCSI, Volume 4, Issue 1, pp10-15, September 2009"

Journal ref Y. M. Chen and B. Wang, "Towards Participatory Design of Multi-agent Approach to Transport Demands ", International Journal of Computer Science Issues, IJCSI, Volume 4, Issue 1, pp10-15, September 2009

The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration

对话的几何学：基于图谱的语言模型揭示多智能体协作的协同团队

Kotaro Furuya, Yuichi Kitagawa

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL；agentic(comments)

AI总结 本文提出一种基于交互的自动团队组建框架，通过构建语言模型图谱揭示多智能体协作的协同团队，实验表明其能发现功能一致的团队并优于随机基线。

Comments Accepted at the AAAI-26 Workshop on LLM-based Multi-Agent Systems: Towards Responsible, Reliable, and Scalable Agentic Systems (LaMAS 2026) as an oral presentation

Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning

Claude Formanek, Asad Jeewa, Jonathan Shock, Arnu Pretorius

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.LG；autonomous agent(comments)

Comments Extended Abstract at Autonomous Agents and Multi-Agent Systems Conference 2023

FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning

FL-MAESTRO：面向资源受限联邦学习的多智能体大语言模型编排框架

Jiajun Wu, Zirui Wang, Jiayu Zhou, Qiang Ye, Steve Drew

机构 * University of Calgary（卡尔加里大学） ； University of Michigan（密歇根大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 FL-MAESTRO是面向资源受限联邦学习的多智能体LLM编排框架，通过三个专业LLM智能体联合决策，在非IID CIFAR-10基准上，准确率与最强能量感知基线相当，浪费轮次能量从超三分之一降至近零。

Comments Accepted at IEEE GLOBECOM 2026

Towards Traffic Modelling of Multi-Agent Systems: The Role of Coordination Topology

面向多智能体系统的流量建模：协调拓扑的作用

Davide Lamagna, Albert Cabellos, Alberto Rodriguez-Natal, Gábor Rétvári, Berta Serracanta

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 本研究针对多智能体LLM系统，通过500次重复运行的多层测量框架，揭示了协调拓扑对LLM请求到达过程的关键影响，相关框架与分析流程已公开。

Comments 7 pages, 5 figures, 4 tables. Published at the ACM SIGCOMM Workshop on Networks for AI Computing (NAIC '26)

G-MARK: Grounded Multi-Agent Reasoning for Cooperative Driving via Knowledge Graphs

G-MARK：基于知识图谱的协同驾驶接地多智能体推理

Bhavya Gupta, Onat Gungor, Tajana Rosing

机构 * University of California, San Diego（加利福尼亚大学圣迭戈分校） ； West Virginia University（西弗吉尼亚大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.LG

AI总结 提出 G-MARK 框架，通过知识图谱实现协同驾驶多智能体推理，提升遮挡推理与控制选择性能，减小通信负载，效果优于现有基线。

Comments Accepted for oral presentation at the 25th IEEE International Conference on Machine Learning and Applications (ICMLA'26)

A Multi-Agent Platform for Automated Enterprise Analytics and Insight Generation

用于自动化企业分析与洞察生成的多智能体平台

Manoj N M, Vijayakrishna S, Manjunath Srinivas, Rohit Pahan

机构 * Rakuten India Enterprise Private Limited（乐天印度企业私人有限公司） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；AI agent(abstract)；分类 cs.AI

AI总结 本文提出基于CrewAI的多智能体框架，含五个专业智能体，经300个测试用例验证，功能准确率95.3%，较单智能体基线提升显著，可用于自动化企业分析与洞察生成。

ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System

ReasFlow：通过基于知识的多智能体系统助力应用数学中以推理为中心的科学发现

Yutong He, Daibo Li, Guohong Li, Jiahe Geng, Zhengyang Huang, Can Ren, Zekun Zhang, Yifan Liu, Shuchen Zhu, Hengrui Zhang, Boao Kong, Ming Sun, Shu Li, Chenyi Li, Jiang Hu, Kun Yuan, Zaiwen Wen, Pingwen Zhang

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title)；AI agent(abstract)；autonomous agent(abstract)

AI总结 针对理论驱动科学发现探索不足的问题，ReasFlow引入以推理为中心的自主智能体系统，通过内部验证循环和知识检索机制减少专家干预，能统一多项科研任务，从最少提示生成高质量论文，在开源基线中表现出色。

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?

从多智能体到单智能体：技能蒸馏何时有益？

Binyan Xu, Dong Fang, Haitao Li, Kehuan Zhang

机构 * The Chinese University of Hong Kong（香港中文大学） ； LIGHTSPEED 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；workflow(abstract)；分类 cs.AI

AI总结 研究探讨了技能蒸馏在多智能体系统到单智能体系统转换中的有效性，提出通过评估指标的拓扑刚性预测技能效用，并引入AdaSkill框架实现自适应蒸馏。

Comments 35 pages, 15 figures, 17 tables

Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation

用于放射科报告结构化与质量保证的多智能体AI系统：独立放射科医师评估

Iryna Hartsock, Cesar Lam, Christopher Otteni, Aliya Qayyum, Robert Gatenby, Cyrillo Araujo, Ghulam Rasool

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；workflow(abstract)；分类 cs.CL

AI总结 本研究开发了一款本地部署的多智能体AI系统，可实现放射科报告结构化与质量保证，经独立放射科医师评估，该系统表现良好，或有助于放射科报告标准化。

Comments 14 pages, 2 figures, 4 tables

PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training

PrivAct: 通过多智能体偏好训练内化上下文隐私保护

Yuhan Cheng, Hancheng Ye, Hai Helen Li, Jingwei Sun, Yiran Chen

机构 * Department of Electrical ； Computer Engineering, Duke University ； Department of Computer \& Information Science \& Engineering, University of Florida 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.CL

AI总结 PrivAct通过多智能体偏好训练，内化上下文隐私保护，提升模型生成行为的隐私合规性，减少信息泄露并保持实用性。

Comments Accepted to ICML 2026