AI Agent

The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning

Jan Blumenkamp, Amanda Prorok

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

Comments Accepted to Conference on Robot Learning (CoRL) 2020. Camera-ready version incorporating rebuttal

Will Agents Replace Us? Perceptions of Autonomous Multi-Agent AI

Nikola Balic

机构 * Faculty of Science University of Split（科学学院 布拉格大学） 纠错

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

Comments 15 pages, 5 figures, code available at https://github.com/nibzard/agent-perceptions

TCellAlign: Cross-study T-cell Populations Alignment with Nomenclature-Guided Multi-Agent Workflow

TCellAlign：使用命名法引导的多智能体工作流程进行跨研究 T 细胞群体对齐

Pengyu Xie, Rongjia Zhou, Zhilin Ou, Junyuan Zhang, Xiang Zhou, Xiaobo Sun, Jiaying Lu, Wenjing Ma

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

AI总结 该研究针对跨研究 T 细胞群体对齐难题，提出 TCellAlign 多智能体框架，含文献检索等模块，能保留原始术语与证据并生成标准化标签。构建基准数据集，实验表明其在语义一致性等方面表现出色，助力 T 细胞相关知识整合与模型发展。

Holonic Active Distillation for Scalable Multi-Agent Learning in Multi-Sensor Systems

Holonic Active Distillation 用于多传感器系统中的可扩展多智能体学习

Dani Manjah, Tim Bary, Benoît Macq, Stéphane Galland

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

AI总结 提出 Holonic Active Distillation 架构，结合聚类流式主动蒸馏，实现多传感器系统中局部专业化与全局泛化的平衡，并适应传感器动态加入与离开。

Comments 21 pages, 5 figures, 2 tables, accepted to EMAS 2025

Journal ref 2025 13th International Workshop on Engineering Multi-Agent Systems

On the Timed Temporal Logic Planning of Coupled Multi-Agent Systems

关于耦合多智能体系统的时序时序逻辑规划

Alexandros Nikou, Dimitris Boskos, Jana Tumova, Dimos V. Dimarogonas

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

AI总结 本文提出一种自动控制器合成方法，用于满足耦合约束的多智能体系统。通过设计分布式抽象和形式验证技术，计算满足高阶任务的个体运行。

Decentralized Abstractions and Timed Constrained Planning of a General Class of Coupled Multi-Agent Systems

去中心化抽象与一般耦合多智能体系统的时约束规划

Alexandros Nikou, Shahab Heshmati-alamdari, Christos Verginis, Dimos V. Dimarogonas

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

AI总结 本文提出一种自动控制器合成方法，针对具有耦合约束的多智能体系统，设计满足MITL规格的控制器并保持连接性。

Cooperative Planning for Coupled Multi-Agent Systems under Timed Temporal Specifications

耦合多智能体系统的 timed 时间规范下的协作规划

Alexandros Nikou, Dimitris Boskos, Jana Tumova, Dimos V. Dimarogonas

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

AI总结 本文提出一种自动控制器合成方法，针对耦合约束下的多智能体系统设计控制输入以满足MITL规范，通过离散化和形式验证技术实现任务满足。

Comments submitted to ACC 2017

Modeling AI-TPACK in Practice Insights from Teachers Multi-Agent Workflow Design

实践中的AI-TPACK建模：来自教师多智能体工作流设计的洞察

Yimeng Sun, Haiyang Xin, Shuang Li, Qiannan Niu, Ching Sing Chai, Lingyun Huang, Gaowei Chen

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

AI总结 研究探讨教师在设计多智能体教学工作流时的行为及认知基础，发现AI-TPACK整合源于系统思维、教学信念和自我效能的动态互动，需针对教师认知行为差异提供差异化支持。

LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading

增强型多智能体强化学习与专家工作流的大型语言模型用于实时点对点能源交易

Chengwei Lou, Zekai Jin, Wei Tang, Guangfei Geng, Jin Yang, Lu Zhang

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

AI总结 本文提出基于大型语言模型-多智能体强化学习的框架，解决实时点对点能源交易中用户技术能力有限、缺乏专家经验及电网安全问题，通过模仿学习生成个性化策略，降低经济成本和电压违规率。

Journal ref IEEE Transactions on Smart Grid (Early Access), 2026

CASCADE: Cascaded Scoped Communication for Multi-Agent Re-planning in Disrupted Industrial Environments

CASCADE：多智能体重新规划中的级联作用域通信

Mingjie Bi

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

AI总结 本文提出CASCADE机制，通过显式作用域控制实现多智能体在受扰工业环境中的重新规划，解决通信预算和延迟约束下的协调问题，提升鲁棒性。

Comments Published at ICLR 2026 Workshop on AI for Mechanism Design and Strategic Decision Making

Strategic Infrastructure Design via Multi-Agent Congestion Games with Joint Placement and Pricing

通过多智能体拥堵博弈的策略性基础设施设计：联合放置与定价

Niloofar Aminikalibar, Farzaneh Farhadi, Maria Chli

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

AI总结 本文提出一种多智能体框架，用于在战略互动下联合进行资源放置和定价决策，通过双层优化模型减少社会成本，实验表明在电动汽车充电领域可降低40%的社会成本。

Comments This paper has been accepted for publication in the Proceedings of the 22nd European Conference on Multi-Agent Systems (EUMAS 2025)

Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation

含义与测量：多智能体概率性视觉语言导航

Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah, Omkar Patil, Thao Nguyen, Nakul Gopalan

机构 * Arizona State University（亚利桑那州立大学） ； Haverford College（哈弗福德学院） 纠错

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

AI总结 本文提出MAPG框架，通过分解语言查询并利用VLM进行语义 grounding，解决复杂度量-语义语言查询的难题，同时引入MAPG-Bench评估指标，展示在现实机器人中的应用效果。

Comments Equal contribution: Swagat Padhan and Lakshya Jain, 9 pages, 6 figures, paper website: https://lakshya-asu.github.io/Meanings-Measurements-Multi-Agent-Probabilistic-Grounding/

MAC: Multi-Agent Constitution Learning

MAC：多智能体宪法学习

Rushil Thareja, Gautam Gupta, Francesco Pinto, Nils Lukas

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫扎德人工智能大学） ； Indraprastha Institute of Information Technology Delhi（德里印度教教派信息科技学院） ； Google DeepMind（谷歌DeepMind） 纠错

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

AI总结 本文提出MAC多智能体宪法学习方法，通过结构化提示优化提升LLM控制效果，实现可解释的规则集生成，优于现有提示优化方法，并在PII标注任务中表现优异。

Comments Code: https://github.com/rushil-thareja/MAC-Multi-Agent-Constitution-Learning | PyPI: https://pypi.org/project/mac-prompt/ | Website: https://www.mac-prompt.com/

COCO: Cognitive Operating System with Continuous Oversight for Multi-Agent Workflow Reliability

COCO：用于多智能体工作流程可靠性的认知操作系统 with 连续监督

Churong Liang, Jinling Gan, Kairan Hong, Qiushi Tian, Zongze Wu, Runnan Li

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

AI总结 COCO通过异步自我监控和自适应错误纠正框架，解决多智能体系统中误差级联问题，提升可靠性和效率。

Multi-Agent gatekeeper: Safe Flight Planning and Formation Control for Urban Air Mobility

多智能体守门人：面向城市空中交通的安全飞行规划与编队控制

Thomas Marshall Vielmetti, Devansh R Agrawal, Dimitra Panagou

机构 * Department of Electrical & Computer Engineering（电气与计算机工程系） ； Department of Robotics（机器人学系） ； Department of Robotics and Department of Aerospace Engineering（机器人学系和航空航天工程系） 纠错

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

AI总结 多智能体守门人框架通过安全轨迹备份和碰撞避免算法，实现城市空中交通中的安全飞行规划与编队控制。

Comments 13 pages, 4 figures, to appear AIAA SciTech 2026

Hierarchical Learning-Based Control for Multi-Agent Shepherding of Stochastic Autonomous Agents

Italo Napolitano, Stefano Covone, Andrea Lama, Francesco De Lellis, Mario di Bernardo

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

TinyMA-IEI-PPO: Exploration Incentive-Driven Multi-Agent DRL with Self-Adaptive Pruning for Vehicular Embodied AI Agent Twins Migration

Zhuoqi Zeng, Yuxiang Wei, Jiawen Kang

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

Compositional Planning for Logically Constrained Multi-Agent Markov Decision Processes

Krishna C. Kalagarla, Matthew Low, Rahul Jain, Ashutosh Nayyar, Pierluigi Nuzzo

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

Comments 6 pages, 1 figure, accepted for publication at the 63rd IEEE Conf. on Decision and Control (2024)

Coordinated Motion Planning: Multi-Agent Path Finding in a Densely Packed, Bounded Domain

Sándor P. Fekete, Ramin Kosfeld, Peter Kramer, Jonas Neutzner, Christian Rieck, Christian Scheffer

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

Comments 21 pages, 14 figures, full version of an extended abstract that is to appear in the proceedings of the 35th International Symposium on Algorithms and Computation (ISAAC 2024)

Optimizing Fuel-Constrained UAV-UGV Routes for Large Scale Coverage: Bilevel Planning in Heterogeneous Multi-Agent Systems

Md Safwan Mondal, Subramanian Ramasamy, Pranav Bhounsule

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

Comments The paper is submitted to MRS 2023

Multi-Agent Path Integral Control for Interaction-Aware Motion Planning in Urban Canals

Lucas Streichenberg, Elia Trevisan, Jen Jen Chung, Roland Siegwart, Javier Alonso-Mora

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

Comments Accepted for presentation at the 2023 IEEE International Conference on Robotics and Automation (ICRA)

Journal ref 2023 International Conference on Robotics and Automation (ICRA)

Multi-agent Multi-target Path Planning in Markov Decision Processes

Farhad Nawaz, Melkior Ornik

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

Comments IEEE Xplore link: https://ieeexplore.ieee.org/document/10154136

Journal ref IEEE Transactions on Automatic Control, VOL. 69, NO. 04, 2024 (tentative)

Integrated Task Assignment and Path Planning for Capacitated Multi-Agent Pickup and Delivery

Zhe Chen, Javier Alonso-Mora, Xiaoshan Bai, Daniel D. Harabor, Peter J. Stuckey

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

Journal ref IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5816-5823, July 2021

ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture

ANX：面向AI代理交互的协议优先设计及其支持的3EX解耦架构

Xu Mingze

机构 * Hangzhou Ziyou Data Technology Co., Ltd.（杭州自由数据科技有限公司） 纠错

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

AI总结 本文提出ANX协议，通过协议创新、架构优化和工具补充，解决AI代理交互中高消耗、碎片化、安全性不足等问题，其核心创新包括代理原生设计、人机交互、轻量应用和可执行SOP。

Comments This open-source AI agent interaction protocol (ANX) is benchmarked against existing protocols (MCP, A2A, ANP, OpenCLI, SkillWeaver, CHEQ, COLLAB-LLM) across four dimensions: tooling, discovery, security, and multi-agent SOP collaboration. Code: https://github.com/mountorc/anx-protocol

DentAgent: Evidence-Centric Multi-Agent Coordination for Multimodal Dental Reasoning

DentAgent：以证据为中心的多智能体协调的多模态牙科推理框架

Zijie Meng, Xiwei Dai, Yixuan Tang, Jin Hao, Yang Feng, Fudong Zhu, Xiaoqiang Liu, Shaosheng Cao, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； Shanghai Jiao Tong University（上海交通大学） ； Angelalign Technology Inc.（时代天使科技有限公司） ； Peking University（北京大学） ； Tsinghua University（清华大学） 纠错

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

AI总结 针对现有牙科AI系统模态或任务局限及证据不可追溯问题，提出以证据为中心的多智能体框架DentAgent，经四个基准测试，其多标签诊断性能超越资深专家17.3个百分点，可用于多模态牙科推理及人群口腔健康评估。

MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation

MACS：面向可靠会话式电商推荐的混合多智能体框架

Juli Huang, Hannah Clay, Sajjad Beygi, Thomas Sarda, Negin Golrezaei, Amin Saberi

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

AI总结 针对固定目录场景下会话式电商推荐的可靠性问题，提出混合多智能体框架MACS，其在单轮、多轮基准测试中均展现出更强的约束合规性与推荐性能。

Comments 9 pages, 2 figures, 8 tables. Will be presenting at Stanford Trust&Safety Conference, already presented at Stanford Market AI Conference

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

EMAS：通过证据引导的修正稳定多智能体系统演化

Chao Fei, Qingyi Si, Kaihua Liang, Yanghua Xiao, Panos Kalnis, Hongcheng Guo

机构 * King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学） ； Fudan University（复旦大学） 纠错

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

AI总结 EMAS 是一种不更新 LLM 参数、利用样本经验修正 MAS 拓扑与提示词的方法，在四个基准和两个 LLM 上提升了准确率并降低了 token 成本，表现优于多数基线方法。

CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity

CyberLLM：面向汽车网络安全的多智能体大语言模型框架，用于自主检测与受管控响应

Nenad Petrovic, Oussama Jeddou, Feres Ben Fraj, Vahid Zolfaghari, Fengjunjie Pan, Andre Schamschurko, Alois Knoll

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

AI总结 CyberLLM是由大语言模型编排的多智能体框架，结合确定性检测层与大语言模型精化，在安全防护下实现汽车漏洞自主检测与修复，在基准测试中覆盖约70%漏洞且零误报，验证了LLM智能体自主防御的可行性。

Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering

推理分歧之处：本地化多智能体辩论

Weijun Gao, Xiang Ding, Haoyang Liu, Tiancheng Xing

机构 * The Chinese University of Hong Kong（香港中文大学） ； Nagoya University（名古屋大学） ； Institute of Science Tokyo（东京科学大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

AI总结 针对多智能体辩论冗余交换完整推理轨迹的问题，提出LMAD协议，通过定位冲突并限制辩论范围，在十个骨干模型上实现宏平均评判准确率提升7.20个百分点。

Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks

通过辩论提升大语言模型性能：针对编码任务的多智能体辩论实证研究

Yong Jin Chun, Qihong Chen, Jiawei Li, Iftekhar Ahmed

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

AI总结 本研究探究多智能体辩论（MAD）在软件工程四类编码任务上的有效性，适配NLP的MAD框架并提出两种变体，证实结构化辩论可提升LLM编码性能，凸显其协作协同效应。

Comments accepted to ACM Transactions on Software Engineering and Methodology (TOSEM)