AI Agent

Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition

多智能体交叉熵方法与单调非线性批评分解

Yan Wang, Ke Deng, Yongli Ren

机构 * School of Computing Technologies, RMIT University（计算技术学院，皇家墨尔本理工大学） 纠错

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

AI总结 多智能体交叉熵方法结合单调非线性批评分解，通过提高高价值联合动作的概率来解决集中-分散不匹配问题，并在连续和离散动作基准上表现优异。

Policy Optimization and Multi-agent Reinforcement Learning for Mean-variance Team Stochastic Games

均值-方差团队随机博弈中的策略优化与多智能体强化学习

Junkai Hu, Li Xia

机构 * School of Mechanical and Electrical Engineering, Shenzhen Polytechnic University（机械与电气工程学院，深圳职业技术大学） ； School of Business, Sun Yat-Sen University（商学院，中山大学） 纠错

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

AI总结 本文提出均值-方差多智能体策略迭代算法，用于解决团队随机博弈中的均值-方差优化问题，通过敏感度优化方法证明算法收敛性并推导平稳点条件。

On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning

多智能体逆强化学习中的可行奖励

Till Freihaut, Giorgia Ramponi

机构 * Department of Computer Science University of Zurich（计算机科学系苏黎世大学） 纠错

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

AI总结 本文提出熵正则化的马尔可夫博弈，解决多智能体逆强化学习中奖励函数的可行集问题，并分析误差对策略学习的影响。

Comments Currently under review

Trust-Based Social Learning for Communication (TSLEC) Protocol Evolution in Multi-Agent Reinforcement Learning

基于信任的社会学习的通信（TSLEC）协议进化在多智能体强化学习中

Abraham Itzhak Weinberg

机构 * AI-WEINBERG, AI Experts, Tel Aviv, Israel（AI-WEINBERG，AI专家，特拉维夫，以色列） 纠错

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

AI总结 TSLEC通过基于信任的社会学习方法，在多智能体强化学习中加速新兴通信，减少收敛次数并提高协议的稳健性。

A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective Analysis

面向多领域低资源情境命名实体识别的多智能体LLM框架：通过知识检索、消歧和反思分析

Wenxuan Mu, Jinzhong Ning, Di Zhao, Yijia Zhang

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

AI总结 KDR-Agent通过知识检索、消歧和反思分析，提升多领域低资源情境下命名实体识别的性能

Comments This paper has been accepted by AAAI 2026 (Main Technical Track)

MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question Generation

MAGMA-Edu：多智能体生成多模态框架用于文本-图表教育问题生成

Zhenyu Wu, Jian Li, Hua Huang

机构 * School of Artificial Intelligence, Beijing Normal University（人工智能学院，北京师范大学） 纠错

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

AI总结 MAGMA-Edu通过多智能体框架实现教育问题生成，提升文本与图像的一致性，达到多模态教育内容生成的新水平。

Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systems

Agent-as-a-Graph: 基于知识图谱的LLM多智能体系统中的工具与智能体检索

Faheem Nizar, Elias Lumer, Anmol Gulati, Pradeep Honaganahalli Basavaraju, Vamse Kumar Subbiah

机构 * Commercial Technology and Innovation Office, PricewaterhouseCoopers（普华永道商业技术与创新办公室） 纠错

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

AI总结 本文提出基于知识图谱的智能体检索方法，通过构建智能体与工具的关系图谱，提升多智能体系统中工具和智能体的检索效果。

Multi-Agent Coordination in Autonomous Vehicle Routing: A Simulation-Based Study of Communication, Memory, and Routing Loops

多智能体在自动驾驶路径规划中的协调：基于仿真的通信、记忆与路径循环研究

KM Khalid Saifullah, Daniel Palmer

机构 * Department of Computer Science（计算机科学系） ； The College of Wooster（沃斯特学院） 纠错

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

AI总结 本研究通过引入对象内存管理（OMM）有效解决了多智能体自动驾驶中的路径循环问题，显著降低了平均旅行时间和等待时间，证明了持久共享内存对动态环境中多智能体协调的必要性。

Hierarchical Adaptive Consensus Network: A Dynamic Framework for Scalable Consensus in Collaborative Multi-Agent AI Systems

分层自适应共识网络：一种用于协作多智能体AI系统可扩展共识的动态框架

Rathin Chandra Shit, Sharmila Subudhi

机构 * Department of CSE, International Institute of Information Technology（计算机科学与工程系，国际信息技术研究所） ； Department of CS, Maharaja Sriramm Chandra Bhanja Deo University（计算机系，马哈拉吉·斯里拉姆·查兰贾德奥大学） 纠错

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

AI总结 本文提出分层自适应共识网络，通过三层架构实现协作多智能体系统中高效的共识达成，显著降低通信开销并确保收敛性。

Comments Submitted to Elsevier

FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videos

FOOTPASS：一个多模态多智能体战术上下文数据集，用于足球比赛视频中的 play-by-play 动作识别

Jeremie Ochin, Raphael Chekroun, Bogdan Stanciulescu, Sotiris Manitsaris

机构 * Center for Robotics, Mines Paris - PSL（机器人中心，巴黎-PSL Mines） 纠错

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

AI总结 FOOTPASS数据集旨在通过多模态和多智能体战术上下文，实现足球比赛视频中play-by-play动作的自动化识别与可靠提取。

S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning

Jiangwen Dong, Zehui Lin, Wanyu Lin, Mingjin Zhang

机构 * PolyU 纠错

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

Comments Accepted by AAAI 2026

Multi-Agent Debate Strategies to Enhance Requirements Engineering with Large Language Models

Marc Oriol, Quim Motger, Jordi Marco, Xavier Franch

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

Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation

Shiyuan Li, Yixin Liu, Qingsong Wen, Chengqi Zhang, Shirui Pan

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

Comments Accepted as an oral presentation by AAAI 2026

MAGIC: Multi-Agent Argumentation and Grammar Integrated Critiquer

Joaquín Jordán, Xavier Yin, Melissa Fabros, Gireeja Ranade, Narges Norouzi

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

Comments Accepted into EAAI 2026

SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding

Shuhao Liao, Weihang Xia, Yuhong Cao, Weiheng Dai, Chengyang He, Wenjun Wu, Guillaume Sartoretti

机构 * Hangzhou International Innovation Institute, Beihang University, China（北京航空航天大学杭州国际创新研究院） ； CoreControl Inc, Hangzhou, China（杭州核心控制公司） ； Department of Mechanical Engineering, National University of Singapore, Singapore（新加坡国立大学机械工程系） 纠错

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

Comments Accepted for presentation at the 2025 IEEE International Conference on Robotics and Automation (ICRA)

Journal ref 2025 IEEE International Conference on Robotics and Automation ICRA pp. 1-7

Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs

Yu Li, Yi Huang, Guilin Qi, Junlan Feng, Nan Hu, Songlin Zhai, Haohan Xue, Yongrui Chen, Ruoyan Shen, Tongtong Wu

机构 * Southeast University（东南大学） ； China Mobile Research Institute（中国移动研究院） ； Monash University（墨尔本大学） 纠错

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

Comments This paper has been ACCEPTED as a FULL PAPER at DASFAA 2025 (Oral)

GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification

Ngoc Bui Lam Quang, Nam Le Nguyen Binh, Thanh-Huy Nguyen, Le Thien Phuc Nguyen, Quan Nguyen, Ulas Bagci

机构 * AI VIETNAM（AI越南） ； Carnegie Mellon University（卡内基梅隆大学） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； PTIT ； Northwestern University（西北大学） 纠错

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

Comments Acccepted in MICCAI Workshop 2025

Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration

Guanchen Wu, Zuhui Chen, Yuzhang Xie, Carl Yang

机构 * Department of Computer Science, Emory University（埃默里大学计算机科学系） ； Department of Statistics, Columbia University（哥伦比亚大学统计系） 纠错

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

Comments Agents4Science 2025 (Spotlight)

Multi-Agent Multimodal Large Language Model Framework for Automated Interpretation of Fuel Efficiency Analytics in Public Transportation

Zhipeng Ma, Ali Rida Bahja, Andreas Burgdorf, André Pomp, Tobias Meisen, Bo Nørregaard Jørgensen, Zheng Grace Ma

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

Journal ref Applied Sciences, 2025, 15(21), 11619

Local Guidance for Configuration-Based Multi-Agent Pathfinding

Tomoki Arita, Keisuke Okumura

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

Comments To be presented at AAAI-26

Multi-Agent Collaborative Fuzzing with Continuous Reflection for Smart Contracts Vulnerability Detection

Jie Chen, Liangmin Wang

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

From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions

Jiayi Li, Xiao Liu, Yansong Feng

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

Comments AAAI-2026

MALBO: Optimizing LLM-Based Multi-Agent Teams via Multi-Objective Bayesian Optimization

Antonio Sabbatella

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

Comments Master's Thesis, University of Milano-Bicocca, 2025

DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding

Dawei Zhu, Rui Meng, Jiefeng Chen, Sujian Li, Tomas Pfister, Jinsung Yoon

机构 * Google Cloud AI Research（谷歌云人工智能研究） ； School of Computer Science, Peking University（北京大学计算机学院） 纠错

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

Key Decision-Makers in Multi-Agent Debates: Who Holds the Power?

Qian Zhang, Yan Zheng, Jinyi Liu, Hebin Liang, Lanjun Wang

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

Explaining Decentralized Multi-Agent Reinforcement Learning Policies

Kayla Boggess, Sarit Kraus, Lu Feng

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

Comments Accepted for oral presentation at AAAI-26

VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction

Stephane Da Silva Martins, Emanuel Aldea, Sylvie Le Hégarat-Mascle

机构 * SATIE - CNRS UMR 8029 Paris-Saclay University, France（巴黎-萨克雷大学） 纠错

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

Comments Paper accepted at WACV 2026

Multi-agent Markov Entanglement

Shuze Chen, Tianyi Peng

机构 * Graduate School of Business, Columbia University（哥伦比亚大学商学院） 纠错

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

Achieving Equilibrium under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning

Zhuhui Li, Chunbo Luo, Liming Huang, Luyu Qi, Geyong Min

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

Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation

Songchen Fu, Siang Chen, Shaojing Zhao, Letian Bai, Ta Li, Yonghong Yan

机构 * Laboratory of Speech and Intelligent Information Processing, Institute of Acoustics, CAS（语音与智能信息处理实验室，声学研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） 纠错

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

Comments The code has been open-sourced in the RDC-pymarl project under https://github.com/linkjoker1006