AI Agent

Shortest Path Set Induced Vertex Ordering and its Application to Distributed Distance Optimal Multi-agent Formation Path Planning

最短路径集诱导的顶点排序及其在分布式距离最优多智能体编队路径规划中的应用

Jingjin Yu

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

AI总结 针对无向图中不可区分智能体移动到任意目标编队的距离最优路径规划问题，提出一种基于最短路径集诱导顶点排序的集中式算法，并首次实现分布式调度，同时保证相同的收敛时间。

Comments Extended the earlier version to 8 Pages, complete with literature review. One additional section on a distributed scheduling algorithm is added

AI Agents with Decentralized Identifiers and Verifiable Credentials

具有去中心化标识符和可验证凭证的AI智能体

Sandro Rodriguez Garzon, Awid Vaziry, Enis Mert Kuzu, Dennis Enrique Gehrmann, Buse Varkan, Alexander Gaballa, Axel Küpper

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

AI总结 提出一种基于W3C去中心化标识符和可验证凭证的框架，使AI智能体在对话初期能够建立跨域信任关系，并实现原型系统验证其可行性。

Comments Accepted for presentation at the 18th International Conference on Agents and Artificial Intelligence 2026

Journal ref 18th International Conference on Agents and Artificial Intelligence (ICAART), 2026, volume 1, pp. 252-259

Cayley Graph Optimization for Scalable Multi-Agent Communication Topologies

Cayley图优化用于可扩展的多智能体通信拓扑

Jingkai Luo, Yulin Shao

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

AI总结 本文提出CayleyTopo，通过优化生成集来最小化直径，以提高多智能体通信拓扑的扩展性、鲁棒性和效率。

Comments Keywords: Multi-agent communication, scalable topology, Cayley graph, diameter minimization

PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection

PhishDebate: 基于大语言模型的多智能体框架用于钓鱼网站检测

Wenhao Li, Selvakumar Manickam, Yung-wey Chong, Shankar Karuppayah

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

AI总结 PhishDebate通过多智能体辩论框架提升钓鱼网站检测的准确性与可解释性，实现高召回率和模块化可配置性。

Comments Please cite as: W. Li, S. Manickam, Y. -W. Chong and S. Karuppayah, "PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection," 2025 IEEE International Conference on Big Data (BigData), Macau, China, 2025, pp. 6606-6615, doi: 10.1109/BigData66926.2025.11401440

Journal ref 2025 IEEE International Conference on Big Data (BigData), Macau, China, 2025, pp. 6606-6615

Bilevel Optimization for Covert Memory Tampering in Heterogeneous Multi-Agent Architectures (XAMT)

针对异构多智能体架构中的隐蔽内存篡改的双层优化

Akhil Sharma, Shaikh Yaser Arafat, Jai Kumar Sharma, Ken Huang

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

AI总结 XAMT通过双层优化方法针对异构多智能体架构中的隐蔽内存篡改问题，提出了一种新的训练时威胁模型，以提升系统安全性。

Comments 10 pages, 5 figures, 4 tables. Conference-style paper (IEEEtran). Proposes unified bilevel optimization framework for covert memory poisoning attacks in heterogeneous multi-agent systems (MARL + RAG)

Distributed Average Consensus in Wireless Multi-Agent Systems with Over-the-Air Aggregation

Themistoklis Charalambous, Zheng Chen, Christoforos N. Hadjicostis

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

Comments 5 pages T. Charalambous, Z. Chen and C. N. Hadjicostis, "Distributed Average Consensus in Wireless Multi-Agent Systems with Over-the-Air Aggregation," 2024 IEEE 25th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Lucca, Italy, 2024, pp. 441-445

A Hybrid Adaptive Nash Equilibrium Solver for Distributed Multi-Agent Systems with Game-Theoretic Jump Triggering

Qiuyu Miao, Zhigang Wu

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

Comments Submitted to Asian Journal of Control. 15 pages, 5 figures. This work extends hybrid dynamical systems theory to multi-agent coordination through distributed Nash equilibrium computation with game-theoretic jump triggering mechanisms

Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning

Min Whoo Lee, Kibeom Kim, Soo Wung Shin, Minsu Lee, Byoung-Tak Zhang

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

Comments 7 pages, 3 figures, Published in AAAI 2024 Workshop (Cooperative Multi-Agent Systems Decision-Making and Learning: From Individual Needs to Swarm Intelligence)

Scalable δ-Level Coherent State Synchronization of Multi-Agent Systems in the Presence of Bounded Disturbances

Donya Nojavanzadeh, Zhenwei Liu, Ali Saberi, Anton A. Stoorvogel

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

Comments 25 pages, 15 figures, This is a preprint of the paper "Scalable δ-Level Coherent State Synchronization of Multi-Agent Systems with Adaptive Protocols and Bounded Disturbances" submitted to the International Journal of Adaptive Control & Signal Processing

Mobility-Aware Resource Allocation for mmWave IAB Networks: A Multi-Agent Reinforcement Learning Approach

Bibo Zhang, Ilario Filippini

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

Comments B. Zhang, I. Filippini, "Mobility-Aware Resource Allocation for mmWave IAB Networks: A Multi-Agent Reinforcement Learning Approach", to appear on IEEE/ACM Transactions on Networking

Energy-Optimal Multi-Agent Navigation as a Strategic-Form Game

Logan Beaver

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

Comments 4 pages, 3 figures. Extended abstract for the 2023 IEEE International Symposium on Multi-Robot and Multi-Agent Systems (MRS 2023)

Multi-agent Collective Construction using 3D Decomposition

Akshaya Kesarimangalam Srinivasan, Shambhavi Singh, Geordan Gutow, Howie Choset, Bhaskar Vundurthy

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

Comments Presented at the Multi-agent Path Finding Workshop at AAAI 2023

QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction

Zikang Zhou, Zihao Wen, Jianping Wang, Yung-Hui Li, Yu-Kai Huang

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

Comments Technical report for the 1st place solution of the Argoverse 2 Multi-Agent Motion Forecasting Competition at the CVPR 2023 Workshop on Autonomous Driving

MLFC: From 10 to 50 Planners in the Multi-Agent Programming Contest

Rafael C. Cardoso, Angelo Ferrando, Fabio Papacchini, Matt Luckcuck, Sven Linker, Terry R. Payne

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

Comments Published in The Multi-Agent Programming Contest 2021: One-and-a-Half Decades of Exploring Multi-Agent Systems

Model-Free Optimal Control of Linear Multi-Agent Systems via Decomposition and Hierarchical Approximation

Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty

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

Comments This paper proposes a hierarchical learning and control framework for model-free LQR of heterogeneous linear multi-agent systems

Learning Distributed Stabilizing Controllers for Multi-Agent Systems

Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, Piyush K. Sharma

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

Comments This paper propose model-free RL algorithms for deriving stabilizing gains of continuous-time multi-agent systems

The Multi-Agent Programming Contest: A résumé

Tobias Ahlbrecht, Jürgen Dix, Niklas Fiekas, Tabajara Krausburg

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

Comments Submitted to the proceedings of the Multi-Agent Programming Contest 2019, to appear in Springer Lect. Notes Computer Challenges Series https://www.springer.com/series/16528

Train Unit Shunting and Servicing: a Real-Life Application of Multi-Agent Path Finding

Jesse Mulderij, Bob Huisman, Denise Tönissen, Koos van der Linden, Mathijs de Weerdt

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

Comments 14 pages, 2 figures, to be published in the 4th International Workshop on Multi-agent Path Finding (2020)

When2com: Multi-Agent Perception via Communication Graph Grouping

Yen-Cheng Liu, Junjiao Tian, Nathaniel Glaser, Zsolt Kira

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

Comments Accepted to CVPR 2020; for the project page, see https://ycliu93.github.io/projects/multi-agent-perception.html

Massive Multi-Agent Data-Driven Simulations of the GitHub Ecosystem

Jim Blythe, John Bollenbacher, Di Huang, Pik-Mai Hui, Rachel Krohn, Diogo Pacheco, Goran Muric, Anna Sapienza, Alexey Tregubov, Yong-Yeol Ahn, Alessandro Flammini, Kristina Lerman, Filippo Menczer, Tim Weninger, Emilio Ferrara

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

Journal ref International Conference on Practical Applications of Agents and Multi-Agent Systems, pp. 3-15. Springer, Cham, 2019

Modeling Normative Multi-Agent Systems from a Kelsenian Perspective

Christiano Braga, Edward Hermann Haeusler, Jéssica S. Santos

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

Comments (A revision of "Normative Multi-Agent Systems and Kelsenian Jurisprudence")

Automated Guidance of Collective Movement in a Multi-Agent Model of Physarum polycephalum

Jeff Jones

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

Comments 2015 - Automated Guidance of Collective Movement in a Multi-Agent Model of Physarum polycephalum, Multi-Agent Models on Swarm Behaviour, Swarm 2015, 28-30 October, Kyoto, Japan

Observation of large-scale multi-agent based simulations

Gildas Morvan, Alexandre Veremme, Daniel Dupont

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

Journal ref Multi-Agent-Based Simulation XII, LNCS 7124, 2012, pp 103-112

Multi-Agent Systems and Blood Cell Formation

Nikolai Bessonov, Ivan Demin, Polina Kurbatova, Laurent Pujo, Vitaly Volpert

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

Journal ref Multi-Agent Systems - Modeling, Interactions, Simulations and Case Studies, InTech (Ed.) (2011) 502

A variant of the multi-agent rendezvous problem

Peter Hegarty, Anders Martinsson, Dmitry Zhelezov

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

Comments 18 pages, 3 figures. None of the authors has any previous experience in this area of research (multi-agent systems), hence we welcome any feedback from specialists

Soft Control on Collective Behavior of a Group of Autonomous Agents by a Shill Agent

Jing Han, Ming Li, Lei Guo

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

Comments 13 papers, 4 figures. Journal paper. This paper proposes a novel idea for intervention to multi-agent systems, called 'soft-control'. A case study is shown: add a shill to a multi-agent system (the vicsek's model) to guide synchronization

Journal ref Journal of Systems Science and Complexity, 2006(19):54-62

TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation

TransMeme：用于跨文化梗图再创作的多智能体框架

Jingyi Zheng, Yule Liu, Zifan Peng, Tianyi Hu, Yuemeng Zhao, Xinhu Zheng, Xinlei He

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Wuhan University（武汉大学） ； Aarhus University（奥胡斯大学） 纠错

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

AI总结 本研究针对跨文化梗图再创作的三大核心挑战，提出多智能体框架TransMeme，经中英双向梗图再创作的人工评估与LLM评判，性能优于所有基线，为该领域未来幽默迁移研究指明方向。

Comments 10 pages, 4 figures. Accepted at the 34th ACM International Conference on Multimedia (ACM MM 2026)

LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems

LiveSim：在多智能体直播生态系统中模拟环境塑造的用户

Jiaqi Xu, Yiran Qiao, Jing Chen, Qiwei Zhong, Xiang Ao, Xueqi Cheng

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； ByteDance China（字节跳动中国） 纠错

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

AI总结 该研究提出基于LLM的LiveSim框架，通过环境塑造的动态用户行为模拟，在真实直播风控数据实验中验证其可提升用户级行为保真度并支持生态系统级分析。

Comments 20 pages, 8 figures, 7 tables

From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvement

从SQL到知识图谱：一种基于大语言模型的多智能体方法及数据模式改进

Dinh-Khanh Pham, Quy-Anh Dang, Lam Mai Thanh, Khanh Bui, Truong-Son Hy

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

AI总结 该研究提出一种LLM驱动的多智能体系统，可将RDBMS自动转换为图数据库，经实验验证其问答准确率及延迟表现均优于传统SQL方案。

SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing

SPAR-Hate：一种由审核员引导的用于双语仇恨言论解析的多智能体框架

Yifan Lyu, Dianqing Lin, Xinran Li, Jiaqi Qiao, Xiujuan Xu

机构 * Dalian University of Technology（大连理工大学） ； Inner Mongolia University（内蒙古大学） 纠错

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

AI总结 针对结构化仇恨言论解析的文化等挑战，提出SPAR-Hate多智能体框架，分解文档为决策单元后从三视角生成判断并仲裁，在基准上实现双语仇恨解析最优结果。

Comments 16 pages, 2 figures. Submitted to EMNLP 2026