AI Agent

An Iterative Approach for Heterogeneous Multi-Agent Route Planning with Resource Transportation Uncertainty and Temporal Logic Goals

Gustavo A. Cardona, Kaier Liang, Cristian-Ioan Vasile

机构 * Mechanical Engineering and Mechanics Department（机械工程与力学系） 纠错

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

AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration

Hyunjn An, Yongwon Kim, Wonduk Seo, Joonil Park, Daye Kang, Changhoon Oh, Dokyun Kim, Seunghyun Lee

机构 * Department of Animation, \ University of Art \& Design Uiwang-si Gyeonggi-do Republic of Korea ； Graduate School of Information, \ University Seoul Republic of Korea ； Department of Animation, \ University of Art \& Design ； Graduate School of Information, \ University 纠错

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

Comments 14 pages, 6 figures

MC-Swarm: Minimal-Communication Multi-Agent Trajectory Planning and Deadlock Resolution for Quadrotor Swarm

Yunwoo Lee, Jungwon Park

机构 * AI Institute of Seoul National University（首尔国立大学人工智能研究所） ； Carnegie Mellon University（卡内基梅隆大学） ； Department of Mechanical System Design Engineering, Seoul National University of Science and Technology (SEOULTECH)（首尔科学技术大学机械系统设计工程系） 纠错

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

Comments 13 pages, 11 figures

EncGPT: A Multi-Agent Workflow for Dynamic Encryption Algorithms

Donghe Li, Zuchen Li, Ye Yang, Li Sun, Dou An, Qingyu Yang

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

Iterative Motion Planning in Multi-agent Systems with Opportunistic Communication under Disturbance

Neelanga Thelasingha, Agung Julius, James Humann, James Dotterweich

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

Heuristic Planner for Communication-Constrained Multi-Agent Multi-Goal Path Planning

Jáchym Herynek, Stefan Edelkamp

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

Comments 8 pages, 6 figures

Multi-Objective Multi-Agent Planning for Discovering and Tracking Multiple Mobile Objects

Hoa Van Nguyen, Ba-Ngu Vo, Ba-Tuong Vo, Hamid Rezatofighi, Damith C. Ranasinghe

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

Comments Accepted to IEEE Transactions on Signal Processing. 16 pages, 10 Figures

Prioritize Team Actions: Multi-Agent Temporal Logic Task Planning with Ordering Constraints

Bowen Ye, Jianing Zhao, Shaoyuan Li, Xiang Yin

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

Comments This article is withdrawn due to errors in the methodology section, specifically concerning the insufficient explanation of the data collection process. Upon review, it's clear that the data sampling methods were not adequately described, potentially leading to misinterpretations of the results

No Panacea in Planning: Algorithm Selection for Suboptimal Multi-Agent Path Finding

Weizhe Chen, Zhihan Wang, Jiaoyang Li, Sven Koenig, Bistra Dilkina

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

Periodic Multi-Agent Path Planning

Kazumi Kasaura, Ryo Yonetani, Mai Nishimura

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

Comments 7 pages with 2 pages appendix and 2 pages reference, 8 figures and 2 tables, to be published in the proceedings of AAAI Conference on Artificial Intelligence (AAAI) 2023

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 37(5) (2023) 6183-6191

Decentralized Multi-Agent Planning for Multirotors: a Fully Online and Communication Latency Robust Approach

Charbel Toumieh

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

Communication-Critical Planning via Multi-Agent Trajectory Exchange

Nathaniel Moore Glaser, Zsolt Kira

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

Comments Accepted to ICRA 2023

Multi-Objective Multi-Agent Planning for Jointly Discovering and Tracking Mobile Object

Hoa Van Nguyen, Hamid Rezatofighi, Ba-Ngu Vo, Damith C. Ranasinghe

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

Comments Accepted for publication to the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). Added algorithm 1, background on MPOMDP and OSPA

A Receding Horizon Approach to Multi-Agent Planning from Local LTL Specifications

Jana Tumova, Dimos V. Dimarogonas

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

Comments Extended version of ACC 2014 paper

CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models

CMU-Drive与V2V-VLA：具备推理能力的协同多智能体统一驾驶基准及车对车视觉-语言-动作模型

Hsu-kuang Chiu, Stephen F. Smith

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)；planning(abstract)；分类 cs.AI

AI总结 本文提出协同多智能体统一驾驶基准CMU-Drive及车对车视觉-语言-动作模型V2V-VLA，解决现有VLA模型缺乏协同能力的问题，构建了协同自动驾驶研究的首个基准并将相关资源开源。

Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis

Agent-as-Peer-Debriefer: 一种基于视角精炼的多智能体定性分析框架

Zhimin Lin, Kun Cheng, Zhiyao Shu, Junhua Fang, Juntao Li, Fan Bai, Jie Gao

机构 * Soochow University（苏州大学） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

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

AI总结 提出一种多智能体框架，通过模拟同行汇报（peer debriefing）并引入理论驱动、数据驱动和应用三种分析视角，提升大语言模型在定性数据分析中的编码质量。

MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems

MANTA：面向自演进多智能体系统的多智能体网络拓扑自适应框架

Mao-xun Huang, Jerry Wang, Yi-Cheng Lai, Zhengxin Zhang, Claire Cardie, Hen-Hsen Huang

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

AI总结 该研究提出MANTA框架，使多智能体系统通信拓扑可在推理阶段自演进，在五类基准测试中平均得分74.0，较最强基线高5.8个百分点，验证了推理阶段自改进可延伸至协作架构。

Enhancing Multi-Agent Communication through Attention Steering with Context Relevance

通过上下文相关性的注意力引导增强多智能体通信

Hongxiang Zhang, Yuan Tian, Tianyi Zhang

机构 * Purdue University（普渡大学） 纠错

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

AI总结 针对LLM多智能体系统中长对话历史导致信息稀释的问题，提出无训练的上下文管理方法Agent-Radar，利用时空衰减机制动态引导注意力，在五个基准上取得最高7.64个绝对点的提升。

The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane

带外元数据对安全自主智能体的重要性：Redpanda 智能体数据平面

Tyler Akidau, Tyler Rockwood, Johannes Brüderl, Marc Millstone

机构 * Redpanda USA / Germany（Redpanda美国/德国） 纠错

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

AI总结 针对自主智能体在安全关键元数据处理上的不可靠性，提出基于带外元数据通道的 Redpanda 智能体数据平面架构，实现访问策略、数据分类和行为约束的确定性执行，并通过多智能体投资组合再平衡系统验证其有效性。

Comments 6 pages, 1 figure. Published at SAO '26 (co-located with ACM CAIS '26)

MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration

MimirRAG：一种集成元数据的金融数据检索多智能体RAG框架

Magnus Samuelsen, Wilmer Nyström, Somnath Mazumdar, Mansoor Hussain, Mikkel Strange

机构 * Copenhagen Business School（哥本哈根商学院） 纠错

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

AI总结 提出MimirRAG多智能体RAG框架，通过元数据集成、表格感知分块和智能体工作流，在金融数据检索中实现89.3%准确率，优于基线。

MonoScale: Scaling Multi-Agent System with Monotonic Improvement

MonoScale: 通过单调改进扩展多智能体系统

Shuai Shao, Yixiang Liu, Bingwei Lu, Weinan Zhang

机构 * Shanghai Jiao Tong University, Shanghai, China（上海交通大学，上海，中国） ； Shanghai Innovation Institute, Shanghai, China（上海创新研究院，上海，中国） 纠错

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

AI总结 本文提出MonoScale框架，通过生成agent条件化熟悉任务、收集交互证据并将其转化为可审计的自然语言记忆，实现多智能体系统的单调性能提升，实验表明其在GAIA和Humanity's Last Exam任务中优于简单扩展和强路由固定池基线。

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

超越个体智能：调查基于大语言模型的多智能体系统的协作、故障归因与自我进化

Shihao Qi, Jie Ma, Rui Xing, Wei Guo, Xiao Huang, Zhitao Gao, Jianhao Deng, Jun Liu, Lingling Zhang, Bifan Wei, Boqian Yang, Pinghui Wang, Jianwen Sun, Jing Tao, Yaqiang Wu, Hui Liu, Yu Yao, Tongliang Liu

机构 * MOE KLINNS Lab（MOE KLINNS实验室） ； School of Computer Science and Technology（计算机科学与技术学院） ； School of Cyber Science and Engineering（网络安全工程学院） ； School of Software Engineering（软件工程学院） ； School of Control Science and Engineering（控制科学与工程学院） ； Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering（陕西省大数据知识工程重点实验室） ； Laboratory for AI and New Forms of Education（人工智能与新型教育实验室） ； Lenovo AI Technology Center, CTOO, Lenovo（联想AI技术中心，联想CTOO） ； Sydney AI Centre, The University of Sydney（悉尼AI中心，悉尼大学） 纠错

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

AI总结 本文探讨了基于大语言模型的多智能体系统中协作、故障归因与自我进化之间的因果关系，提出LIFE进展模型，系统分类各阶段并揭示其依赖与约束，为自适应多智能体系统提供理论框架和研究方向。

Progressive Multi-Agent Reasoning for Biological Perturbation Prediction

逐步多智能体推理用于生物扰动预测

Hyomin Kim, Sang-Yeon Hwang, Jaechang Lim, Yinhua Piao, Yunhak Oh, Woo Youn Kim, Chanyoung Park, Sungsoo Ahn, Junhyeok Jeon

机构 * KAIST（韩国国立科学技术院） 纠错

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

AI总结 本文提出LINCSQA基准和PBio-Agent框架，通过整合难度感知任务序列与迭代知识细化，提升复杂化学扰动下基因调控预测的准确性与解释性。

Comments 17 pages, 4 figures, 9 tables

Security Considerations for Multi-agent Systems

多智能体系统中的安全考虑

Tam Nguyen, Moses Ndebugre, Dheeraj Arremsetty

机构 * Crew Scaler ； North Carolina A&T State University（北卡罗来纳A&T州立大学） ； MITRE ATLAS ； ATFAA-SHIELD ； CDAO Generative AI Responsible AI Toolkit（CDAO生成式AI责任AI工具包） 纠错

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

AI总结 本文系统分析了多智能体系统（MAS）的安全威胁，并评估了16个AI安全框架，发现非确定性和数据泄露是最薄弱环节，OWASP和CDAO在设计和开发阶段表现突出。

Comments A Crew Scaler (501c3 pending org)'s response to NIST RFI 2026-00206. Check back for updated versions. Tam Nguyen is the corresponding author

Architecture Matters for Multi-Agent Security

多智能体安全中的架构问题

Ben Hagag, William L. Anderson, Christian Schroeder de Witt, Sarah Scheffler

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Oxford Witt Lab, University of Oxford（牛津Witt实验室，牛津大学） 纠错

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

AI总结 本文研究多智能体系统设计决策对任务性能与攻击抵御之间的权衡，通过三个环境和13种架构配置，分析智能体角色、通信拓扑和内存三个关键设计选择的影响。

Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence

单智能体扩展无法实现多智能体智能：迈向具有原生多智能体智能的基础模型

Shuyue Hu, Haoyang Yan, Yiqun Zhang, Yang Chen, Dongzhan Zhou, Lei Bai

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

AI总结 本文指出单智能体扩展无法实现多智能体智能，提出构建具有原生多智能体智能的基础模型的关键方向。

TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems

Ishan Kavathekar, Hemang Jain, Ameya Rathod, Ponnurangam Kumaraguru, Tanuja Ganu

机构 * International Institute of Information Technology, Hyderabad（国际信息科技研究所，海得拉巴） ； Microsoft Research, India（微软研究院，印度） 纠错

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

Comments Accepted at ICML 2025 MAS Workshop. This version includes additional experiments and analysis

Agentic Nesting: A New Methodology for Existing Enterprise Application Integration and Services

智能体嵌套：现有企业应用集成与服务的新方法论

Xi Wang, Kun Li, Xianyao Ling, Gang Yin, Liang Zhang, Jiang Wu, Wenbo Lei, Jun Xu, Annie Wang, Fu Zhang, Weizhe Wang

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

AI总结 针对企业应用集成的传统方法存在的缺陷，本文提出Agentic Nesting多智能体协作框架，构建分层嵌套的智能体结构，实现跨应用的对话式集成，探索其在异构系统等场景的泛化潜力。

Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution

多智能体博弈中的层次化控制：基于LLM的规划与RL执行

Jannik Hösch, Alessandro Sestini, Florian Fuchs, Amir Baghi, Joakim Bergdahl, Iolanda Leite, Konrad Tollmar, Jean-Philippe Barrette-LaPierre, Linus Gisslén

机构 * Electronic Arts ； KTH Royal Institute of Technology（皇家理工学院） 纠错

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

AI总结 提出LLM作为中央策略控制器选择RL技能策略的层次化架构，在2v2对抗环境中达到与手工BT相当的胜率，且被感知为最类人。

Comments 12 pages, 9 figures

SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing

SPEAR：智能合约审计中的多智能体协调工程案例研究

Indraveni Chebolu, Arnab Mallick, Harmesh Rana

机构 * Centre for Development of Advanced Computing（先进计算发展中心） 纠错

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

AI总结 SPEAR通过多智能体框架提升智能合约审计效率，采用风险感知启发式优先级分配与自动修复策略，实验证明其在协调性、恢复能力和资源利用方面的优势。

Comments Accepted at 14th International Workshop on Engineering Multi-Agent Systems(EMAS @ AAMAS)