AI Agent

SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

SentinelAgent：意图验证的委托链用于安全的联邦多智能体AI系统

KrishnaSaiReddy Patil

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

AI总结 本文提出SentinelAgent框架，通过委托链计算和意图保留协议，实现联邦多智能体AI系统的安全委托验证，验证生命周期在DelegationBench v4上达到100%TPR且0%FPR。

Comments 12 pages, 2 figures, 9 tables. Includes TLA+ mechanical verification, DelegationBench v4 benchmark (516 scenarios), live LangChain agent integration, and independent red-team evaluation

Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards

通过图神经网络驱动的内在奖励增强去中心化MARL中的异质多智能体协作

Jahir Sadik Monon, Deeparghya Dutta Barua, Md. Mosaddek Khan

机构 * Independent University Bangladesh（独立大学Bangladesh） ； Penta Global Ltd（Penta全球有限公司） ； University of Dhaka, Bangladesh（达卡大学，Bangladesh） 纠错

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

AI总结 CoHet通过图神经网络驱动的内在动机提升去中心化MARL中异质智能体协作性能

Comments Full paper version for AAMAS 2025 (https://ifaamas.org/Proceedings/aamas2025/pdfs/p2681.pdf), 9 pages, 5 figures

Journal ref Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025), pages 2681-2683, 2025

Heterogeneous RBCs via Deep Multi-Agent Reinforcement Learning

异质性RBCs通过深度多智能体强化学习

Federico Gabriele, Aldo Glielmo, Marco Taboga

机构 * Università La Sapienza di Roma（罗马拉·索菲亚大学） ； Banca d’Italia（意大利银行） 纠错

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

AI总结 本文提出MARL-BC框架，结合深度多代理强化学习与RBC模型，解决传统模型在异质性建模方面的局限性。

Comments 14 pages, 10 figures

Journal ref Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026, https://cyprusconferences.org/aamas2026/)

B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning

B3C: 一种针对离线多智能体强化学习的极简方法

Woojun Kim, Katia Sycara

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

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

AI总结 B3C通过引入批评者剪裁和非线性价值分解，有效解决离线多智能体强化学习中的过估计问题，提升性能。

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

MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling

MAViS：一个用于长序列视频叙事的多智能体框架

Qian Wang, Ziqi Huang, Ruoxi Jia, Paul Debevec, Ning Yu

机构 * Virginia Tech（弗吉尼亚理工大学） ； Nanyang Technological University（南洋理工大学） ； Eyeline Studios（Eyeline工作室） 纠错

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

AI总结 MAViS通过多智能体协作框架提升长序列视频生成的辅助能力、视觉质量和表达性，支持多模态输出。

Comments Video Generation Agent

ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems

ElecTwit：多智能体社交系统中说服研究的框架

Michael Bao

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

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

AI总结 ElecTwit通过模拟政治选举中的社交媒体互动，研究多智能体系统中说服现象的影响因素及不同模型架构对说服动态的作用。

Comments In proceedings of 2025 IEEE International Conference on Agentic AI (ICA)

A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building

一种灵活的多智能体LLM-人类框架，用于快速的人类验证工具构建

Daull Xavier, Patrice Bellot, Emmanuel Bruno, Vincent Martin, Elisabeth Murisasco

机构 * Toulon Univ（图卢兹大学） ； Aix Marseille Univ（阿维尼翁-马赛大学） ； CNRS（国家科学研究中心） ； LIS（信息系统实验室） 纠错

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

AI总结 该研究提出了一种灵活的多智能体框架，通过人类反馈和强化学习，实现快速的人类验证工具构建，适用于复杂迭代任务。

Journal ref 2025 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), Nov 2025, Londres, United Kingdom

MASA: LLM-Driven Multi-Agent Systems for Autoformalization

Lan Zhang, Marco Valentino, André Freitas

机构 * Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系） ； School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院） ； Idiap Research Institute（Idiap研究 institute） ； National Biomarker Centre, CRUK Manchester Institute（国家生物标志物中心，CRUK曼彻斯特研究所） 纠错

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

Comments EMNLP 2025 Demo camera-ready. Code and data are available at: https://github.com/lanzhang128/multi_agent_autoformalization

Preventing Rogue Agents Improves Multi-Agent Collaboration

Ohav Barbi, Ori Yoran, Mor Geva

机构 * Blavatnik School of Computer Science and AI, Tel Aviv University（布劳维茨克计算机科学与人工智能学院，特拉维夫大学） 纠错

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

Comments Accepted as a spotlight to REALM (First Workshop for Research on Agent Language Models) at ACL 2025

Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning

Lukas Schäfer, Oliver Slumbers, Stephen McAleer, Yali Du, Stefano V. Albrecht, David Mguni

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

Comments Published at 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025)

Transient Multi-Agent Path Finding for Lifelong Navigation in Dense Environments

Jonathan Morag, Noy Gabay, Daniel koyfman, Roni Stern

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

Comments Submitted to The 35th International Conference on Automated Planning and Scheduling (ICAPS 2025)

Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management

Zhenglong Li, Vincent Tam, Kwan L. Yeung

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

Comments In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems

Context-aware Communication for Multi-agent Reinforcement Learning

Xinran Li, Jun Zhang

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

Comments Accepted by the 23nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024)

Signifiers as a First-class Abstraction in Hypermedia Multi-Agent Systems

Danai Vachtsevanou, Andrei Ciortea, Simon Mayer, Jérémy Lemée

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

Journal ref Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (2023) p. 1200-1208

Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization

Xiangsen Wang, Xianyuan Zhan

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

Comments Accepted by the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

Mediated Multi-Agent Reinforcement Learning

Dmitry Ivanov, Ilya Zisman, Kirill Chernyshev

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

Journal ref AAMAS '23, Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (May 2023) Pages 49-57

Phantom -- A RL-driven multi-agent framework to model complex systems

Leo Ardon, Jared Vann, Deepeka Garg, Tom Spooner, Sumitra Ganesh

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

Comments 2022 ACM International Conference on Artificial Intelligence in Finance - Benchmarks for AI in Finance Workshop 2023 Autonomous Agents and Multiagent Systems - Extended Abstract

The challenge of redundancy on multi-agent value factorisation

Siddarth Singh, Benjamin Rosman

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

Comments Published at the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023). 2 Pages, 1 Figure

Coordinated Multi-Agent Pathfinding for Drones and Trucks over Road Networks

Shushman Choudhury, Kiril Solovey, Mykel Kochenderfer, Marco Pavone

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

Comments Accepted to Autonomous Agents and Multiagent Systems, 2022

Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice

Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael Wooldridge

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

Comments Accepted to the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-21)

Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning

Xueguang Lyu, Christopher Amato

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

Journal ref Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, pp. 798-806. 2020

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery

Jiachen Yang, Igor Borovikov, Hongyuan Zha

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

Comments Published at International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020)

Learning Multi-agent Communication under Limited-bandwidth Restriction for Internet Packet Routing

Hangyu Mao, Zhibo Gong, Zhengchao Zhang, Zhen Xiao, Yan Ni

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

Comments This paper proposes a gating mechanism with several crucial designs for adaptively prunning the unprofitable communication messages among multiple agents, such that the limited-bandwidth restriction existing in many real-world muli-agent systems can be resolved. Experiments show that our method can prune quite a lot of unprofitable messages with little damage to the performance

General Principles of Learning-Based Multi-Agent Systems

David H. Wolpert, Kevin R. Wheeler, Kagan Tumer

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

Comments 7 pages, 6 figures

Journal ref Proceedings of the Third International Conference on Autonomous Agents, Seatle, WA 1999

Fluid Structure, Rigid Record: A Layered Organizational Design Framework for Agent-Native Organizations

流体结构，刚性记录：面向智能体原生组织的分层组织设计框架

Lucian Zhu

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

AI总结 本文提出一种分层框架，分离智能体原生组织的持久与动态层，通过多类智能体与角色组实现灵活执行与刚性底层，已实现原型并完成小样本实验，贡献为可证伪的组织设计治理框架。

From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architecture for Hospital AI Systems

从孤立算法到合规优先的智能体平台：面向医院AI系统的多层架构

Manideep Dhar, Ritwik Singh, Sharat Chandra Kumar Manikonda

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

AI总结 针对医院AI部署孤立、规模化难的问题，提出含智能体编排、合规策略、隐私保护数据层的多层架构，通过原型验证可减少任务耗时与文档工作量，为医院AI平台建设提供实用蓝图。

Comments Peer-reviewed published article

Journal ref IJISRT, 11-2026(5), IJISRT26MAY1651

SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy

SynAgent：通过独狼到协作代理协同实现通用化的人形机器人操作

Wei Yao, Haohan Ma, Hongwen Zhang, Liangjun Xing, Zhile Yang, Yuanjun Guo, Yunlian Sun, Yebin Liu

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院） ； Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院） ； School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院） ； Department of Automation, Tsinghua University（清华大学自动化系） ； College of Artificial Intelligence, Nanjing Forestry University（南京林业大学人工智能学院） 纠错

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

AI总结 本文提出SynAgent框架，通过独狼到协作代理协同转移单agent人-物体交互技能，实现可扩展且物理合理的协作操作，实验显示其在协作模仿和轨迹条件控制方面优于现有基线。

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

《智能体AI的搭车指南：从基础到系统》

Haggai Roitman

机构 * Haggai Roitman 纠错

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

AI总结 本文为构建自主AI系统提供全面实践参考，覆盖从Transformer架构、训练优化到对齐、推理、检索增强生成、记忆系统、智能体设计模式及多智能体协调的完整技术栈。

Comments version 1.3

Agentic-SecPBFT: Agentic AI-Driven Proactive Security Framework for Wireless PBFT Consensus in Mobile Ad-Hoc Networks

Agentic-SecPBFT：用于移动自组织网络中无线PBFT共识的智能AI驱动主动安全框架

Haoxiang Luo, Yinqiu Liu, Ruichen Zhang, Guangyuan Liu, Gang Sun, Hongfang Yu, Zhu Han, Dong In Kim

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

AI总结 针对移动自组织网络中PBFT协议的安全问题，利用智能AI范式构建多智能体系统，智能体用分层MADQN算法实时学习执行安全策略，提升共识过程完整性，模拟显示其性能良好。

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

FlowBank: 通过预计算与复用实现查询自适应智能体工作流优化

Lingzhi Yuan, Chenghao Deng, Fangxu Yu, Souradip Chakraborty, Mohammad Rostami, Furong Huang

机构 * University of Maryland, College Park（马里兰大学哥伦比亚公园分校） ； Amazon（亚马逊） 纠错

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

AI总结 提出FlowBank框架，通过预计算多样化工作流并压缩为紧凑组合，在推理时自适应选择最优工作流，平衡性能与成本，在五个基准上平均得分最高且成本可控。