AI Agent

A new approach of designing Multi-Agent Systems

Sara Maalal, Malika Addou

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

Comments 10 pages, 12 figures, A practical application of a method of designing multi-agent systems based on the AUML language and the MDA approach at "the 4th IEEE Workshop on Information Technologies and Communication (WOTIC'11)", Casablanca, 13 - 15 October 2011, International Journal of Advanced Computer Science and Applications(IJACSA) Volume 2 No. 11 November 2011

The Impact of Social Networks on Multi-Agent Recommender Systems

Hamilton Link, Jared Saia, Terran Lane, Randall A. LaViolette

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

Comments 12 pages, 4 figures. Published in the Proceedings of the Workshop on Cooperative Multi-Agent Learning (ECML/PKDD '05). Resubmitted to fix citations and metadata

Agentic Large Language Models, a survey

代理大语言模型：综述

Aske Plaat, Max van Duijn, Niki van Stein, Mike Preuss, Peter van der Putten, Kees Joost Batenburg

机构 * Leiden University Leiden Netherlands ； Leiden University \& AI Lab, Pegasystems Leiden Netherlands ； Leiden University ； Leiden University \& AI Lab, Pegasystems 纠错

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

AI总结 本文综述了代理大语言模型的研究现状，探讨了其在医疗诊断、物流和金融分析等领域的应用，并提出通过推理、行动和交互提升大语言模型能力的未来研究方向。

Comments Website: https://askeplaat.github.io/agentic-llm-survey-site/

Journal ref JAIR volume 84, article 29, December 2025

On Some Fundamental Problems for Multi-Agent Systems Over Multilayer Networks

Daniel J. Rosenkrantz, Madhav V. Marathe, Zirou Qiu, S. S. Ravi, Richard E. Stearns

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

Comments This is a complete version of the paper (with the same title) that will appear in Proc. of the 24th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS 2025), Detroit, MI, May 2025

Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning

Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson

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

Comments This work as been accepted as an Extended Abstract in Proc. of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), N. Agmon, M. E. Taylor, E. Elkind, M. Veloso (eds.), May 2019, Montreal, Canada

Journal ref Auton Agent Multi-Agent Syst 35, 25 (2021)

Refined Hardness of Distance-Optimal Multi-Agent Path Finding

Tzvika Geft, Dan Halperin

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

Comments Accepted to Autonomous Agents and Multi-Agent Systems (AAMAS 2022)

Automatic Verification of Parameterised Interleaved Multi-Agent Systems

Panagiotis Kouvaros, Alessio Lomuscio

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

Comments 8 pages with 1 figure; Published in the Proceedings of the 12th International Conference on Autonomous Agents and Multi-Agent systems (AAMAS13). Saint Paul, MN, USA

GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix

GraniKV：面向具有长共享前缀的多智能体系统的非对称粒度KV缓存分页

Jinhyun Jeon, Sungjoo Yoo

机构 * Seoul National University（首尔大学） 纠错

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

AI总结 GraniKV是首个将非对称分页粒度应用于生产分页服务引擎KV缓存的系统，通过将共享前缀和后缀分别分配至不同存储池，在多智能体服务场景下显著提升了输出令牌吞吐量。

ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems

ETHOS：面向临床多智能体系统的模块化伦理框架

Rakesh Sharma, Sydney Pugh, Cameron Beeche, Pankhuri Singhal, Rachel Wu, Margaret Eby, Jeffrey Duda, James Gee, Kyra O'Brien, Hersh Sagreiya, Marina Serper, Victoria Gershuni, Angela Bradbury, Anurag Verma, Eric Eaton, Kevin B. Johnson, Walter Witschey

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

AI总结 ETHOS是可与现有临床多智能体系统集成的模块化伦理框架，通过分层治理提升决策可靠性，将AI伦理原则转化为可部署的安全保障。

Comments Preprint of an article submitted for consideration in Pacific Symposium on Biocomputing \textcopyright\ 2027 World Scientific Publishing Company. \url{https://psb.stanford.edu/}

When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL

何时通信：多智能体强化学习中基于信念分布与KL散度的原则性门控机制

Teoman Kaman

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

AI总结 本文提出一种多智能体强化学习中基于KL散度的原则性通信门控机制，在Predator-Prey和MPE基准测试中，该方法在复杂场景下的性能优于IC3Net等基线方法，还能改进潜在表示以提升智能体协调效果。

Comments 8 pages, 5 figures

Population-Scalable Multi-Agent World Modeling

支持种群规模扩展的多智能体世界建模

Renjie Zhao, Yuxiang Wu, Mingyu Zhang, Jiaxin Li, Sisi Li, Yimin Sheng, Tianxi Tan, Zhenkai Zhang, Jianyi Zhu, Yong-Lu Li

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 针对多智能体世界模型的种群可扩展性问题，提出无需重训练即可扩展至任意智能体数量的Khora模型，通过解耦世界状态演化与渲染实现跨视图一致性，验证了泛化性并构建了实时交互系统。

Comments Technical report. Project page: https://rhos.ai/research/khora. Online demo: https://ophilus.ai/khora

Creativity in LLM-based Multi-Agent Systems: A Survey

Yi-Cheng Lin, Kang-Chieh Chen, Zhe-Yan Li, Tzu-Heng Wu, Tzu-Hsuan Wu, Kuan-Yu Chen, Hung-yi Lee, Yun-Nung Chen

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

Comments 23 pages

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), pages 27572-27595

TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials

TeachMateGPT：面向科学课程材料的多智能体知识基教学评估生成框架

Fatema Tuj Johora Faria, Mukaffi Bin Moin, M. F. Mridha, Jubayer Al Mahmud

机构 * Ahsanullah University of Science and Technology（阿赫桑乌拉科技大学） ； American International University - Bangladesh（孟加拉国美国国际大学） ； Jashore University of Science and Technology（杰索尔科技大学） 纠错

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

AI总结 TeachMateGPT作为多智能体知识基框架，通过四项改进解决现有RAG系统局限，生成的科学评估题提升了忠实度与相关性，相关数据集经教师评分验证。

CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA

CLAIR-Fin：用于跨模态金融问答中声明级验证与自适应辩论的对抗性多智能体框架

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain

机构 * Ahsanullah University of Science and Technology（阿萨努拉科技大学） ； Jashore University of Science and Technology（杰索尔科技大学） ； American International University - Bangladesh（孟加拉国美国国际大学） 纠错

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

AI总结 本研究提出CLAIR-Fin九智能体框架，针对跨模态金融问答的声明级验证与自适应辩论，在BB-FinQA-X数据集上提升了模型忠实度，且弃权比例合理，优于相关基线方法。

MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

MARC v1：一个用于临床AI推理与协作的开源多智能体框架

Saisha Shetty, Satvik Tripathi, Austin Lin, Colin Zhao, Theodore Kim, Don Enwerem, Jacinta Arnold, Shahriar Faghani, Tessa S Cook

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

AI总结 该研究提出开源多智能体框架MARC v1，以确定性多智能体编排替代整体式LLM提示用于临床推理，含角色专业化智能体与分解器模块，支持多部署方式，具备模型无关、可解释等特性。

Comments 13 pages, 4 figures

Learning Latency-Aware Orchestration for Multi-Agent Systems

学习面向延迟的并行多智能体系统编排

Xi Shi, Mengxin Zheng, Qian Lou

机构 * University of Central Florida（中央佛罗里达大学） 纠错

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

AI总结 本文提出LAMaS框架，通过显式优化关键路径降低多智能体系统并行执行的延迟，提升效率和性能。

Comments Preprint. Previously this version appeared as arXiv:2607.13359 which was submitted as a new work by accident

Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning

智能体策略组合是否安全？重新思考合作多智能体强化学习中的后继特征迁移

Zijian Zhao, Sen Li

机构 * The Hong Kong University of Science and Technology（香港科技大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

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

AI总结 针对多智能体强化学习中独立策略组合不安全的问题，提出MA-USFA分层方法，兼顾策略组合的安全性与灵活性，无需任务适配即可部署。

Social Chain of Thought: A Multi-Agent Architecture Grounded in Medical Differential Diagnosis Methodology

社会思维链：一种基于医学鉴别诊断方法论的多智能体架构

Del Coburn, Scott Sanner, Dan Silver

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

AI总结 本文提出基于医学鉴别诊断方法论的多智能体架构SCoT，通过多轮专家协作提升复杂病例诊断召回率，其优势无法通过单一推理实现。

Comments 14 pages, 9 figures, 6 tables

MADQRL: Distributed Quantum Reinforcement Learning Framework for Multi-Agent Environments

MADQRL：多智能体环境的分布式量子强化学习框架

Abhishek Sawaika, Samuel Yen-Chi Chen, Udaya Parampalli, Rajkumar Buyya

机构 * Brookhaven National Laboratory（布鲁克海文国家实验室） 纠错

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

AI总结 本文提出MADQRL框架，通过分布式方法解决高维多智能体环境中的强化学习挑战，实现约10%的改进。

Comments Accepted in QC4C3 Workshop at IEEE QCNC, 2026

Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits

多智能体多臂老虎机中的公平算法与探针

Tianyi Xu, Jiaxin Liu, Nicholas Mattei, Zizhan Zheng

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

AI总结 本文提出了一种多智能体多臂老虎机框架，通过引入探针机制在保证公平性的同时提升系统性能。

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 32, pp. 27332-27340, 2026

Robust Multi-Agent Bandits with Heavy-Tailed Rewards and Information Asymmetry

具有重尾奖励和信息不对称的鲁棒多智能体多臂老虎机

Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang

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

AI总结 该研究针对重尾奖励和信息不对称的多智能体多臂老虎机问题，为三种信息不对称场景开发鲁棒分散式算法，通过实验验证了理论结果并阐明相关权衡。

Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization

通过信息瓶颈和向量量化实现带宽高效的多智能体通信

Ahmad Farooq, Kamran Iqbal

机构 * Department of Electrical and Computer Engineering, University of Arkansas at Little Rock（电气与计算机工程系，阿肯色大学小岩分校） 纠错

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

AI总结 本研究通过信息瓶颈与向量量化方法，实现多智能体通信的带宽高效优化，提升协调性能并减少带宽消耗。

Comments Accepted at IEEE ICRA 2026, Vienna, Austria. 8 pages, 4 figures, 4 tables. v2: replaces v1 with the accepted camera-ready version and corrects a typo in the bandwidth reduction (41.4% -> 71.4%) in the abstract, Sec. I, Fig. 2 caption, Sec. VI and Sec. VII. Sec. V-A and Table I (800 vs 2800 bits/episode) were already correct; no results or conclusions changed

MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning

MARA：流匹配引导的多智能体资源分配，用于计算资源高效学习

Hanye Zhao, Muning Wen, Yong Yu, Weinan Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 研究并发任务的离散计算节点分配问题，提出MARA方法，结合条件流匹配与多智能体策略，在三类工作负载下完成任务率优于基准LARA。

Comments 10 pages, 4 figures, 6 tables

Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments

Social Gym与SPaRTan：通过多智能体游戏锦标赛对LLM社会推理进行基准测试与改进

Keyu He, Xuhui Zhou, Maarten Sap

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

AI总结 该研究推出Social Gym多智能体社会游戏环境与SPaRTan自博弈反思迁移方法，前者可客观基准测试LLM社会推理，后者可提升GPT-5-mini的弱角色表现，为改进LLM社会推理提供了可复现基础。

STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs

STEMMA：用于评估大语言模型（LLM）自我身份一致性的对抗性多智能体框架

Nuthakki Siva Gopala Krishna, Kanishka Jain

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

AI总结 本研究针对LLM自我身份一致性评估问题，提出对抗性多智能体框架STEMMA，结合手动设计的对抗性提示开展实验，发现多数LLM存在自我表征不一致的问题。

Comments 15 pages

Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design

验证驱动的闭环多智能体大语言模型框架：面向符合代码规范的结构设计

Jianbin Luo, Weibin Lin, Yiran Lin, Qing Wei, Wei Guo

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

AI总结 本研究提出验证驱动的闭环多智能体LLM框架，通过耦合有限元验证系统与双节点结构提升结构设计的代码合规性，开源基准与脚本，性能提升显著且具可复现性。

Comments 20 pages, 21 figures

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

不只是RLHF：为何仅对齐不足以解决多智能体趋同

Adarsh Kumarappan, Ananya Mujoo

机构 * California Institute of Technology（加州理工学院） ； Evergreen Valley College（艾弗绿谷学院） 纠错

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

AI总结 本文研究了多智能体系统在模拟同伴分歧下的错误率问题，发现预训练基础模型与指令模型存在相似的替换模式，且错误率较高。通过激活修补发现错误集中在中间层，修复后可恢复大部分正确率差距。研究还指出压力抑制了清洁推理特征，而非激活新的趋同回路。

When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs

何时潜在通信能发挥作用？多智能体大语言模型中中继键值缓存的因果审计

Jiaming Cheng, Subhransu Das, Rajiv Ramnath

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

AI总结 该研究通过因果审计多智能体LLM的中继KV缓存，发现仅当接收方需要发送方私有信息时，潜在通信才会发挥作用，且不匹配缓存审计是验证潜在想法传输的必要手段。

Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization

基于多智能体视角偏好优化的性别歧视检测学习

Hadi Mohammadi, Tina Shahedi, Robert A. Bagheri, Mehdi Dastani, Masoume M. Raeissi

机构 * Utrecht University（乌得勒支大学） ； Wageningen University & Research（瓦赫宁根大学及研究中心） 纠错

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

AI总结 本研究针对性别歧视检测中标注分歧问题，提出MAP-PO框架，通过聚类标注者并训练对应智能体，结合个体与团队奖励协调智能体，实验验证了聚类训练及团队信号的必要性。

Comments 17 pages, 12 figures, 14 tables. Preprint; under review at EACL 2027 (ACL Rolling Review, August 2026 cycle). Code and data: https://github.com/mohammadi-hadi/MAP-PO

FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation

FinRpt：用于权益研究报告生成的数据集、评估系统及基于大语言模型的多智能体框架

Song Jin, Shuqi Li, Shukun Zhang, Rui Yan

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

AI总结 本文首次明确权益研究报告生成任务，推出含数据集、评估系统的FinRpt基准，提出多智能体框架FinRpt-Gen，实验验证其有效性，相关代码与数据集公开。

Comments AAAI 2026