AI Agent - arXivDaily 专题

2401.03630 2024-02-12 cs.MA cs.AI cs.CL 90%

Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet

Weizhe Chen, Sven Koenig, Bistra Dilkina

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

2402.04268 2024-02-08 cond-mat.soft cs.AI cs.CL q-bio.BM 90%

ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning

A. Ghafarollahi, M. J. Buehler

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

2311.06622 2023-11-27 cs.AI cs.CL 90%

TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System

Haoyuan Li, Hao Jiang, Tianke Zhang, Zhelun Yu, Aoxiong Yin, Hao Cheng, Siming Fu, Yuhao Zhang, Wanggui He

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

2309.16534 2023-09-29 cs.CV cs.AI cs.LG cs.RO 90%

MotionLM: Multi-Agent Motion Forecasting as Language Modeling

Ari Seff, Brian Cera, Dian Chen, Mason Ng, Aurick Zhou, Nigamaa Nayakanti, Khaled S. Refaat, Rami Al-Rfou, Benjamin Sapp

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

Comments To appear at the International Conference on Computer Vision (ICCV) 2023

2205.01927 2023-05-22 cs.LG cs.AI cs.RO 90%

Probabilistic Symmetry for Multi-Agent Dynamics

Sophia Sun, Robin Walters, Jinxi Li, Rose Yu

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

2208.04237 2022-08-11 cs.MA cs.AI cs.LG 90%

Multi-Agent Reinforcement Learning for Long-Term Network Resource Allocation through Auction: a V2X Application

Jing Tan, Ramin Khalili, Holger Karl, Artur Hecker

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

Comments arXiv admin note: substantial text overlap with arXiv:2204.02267

2206.13754 2022-06-29 cs.MA cs.AI cs.LG 90%

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

Joe Eappen, Suresh Jagannathan

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

Comments ECML-PKDD 2022

2104.00563 2022-02-14 cs.RO cs.AI cs.CV cs.LG cs.MA 90%

Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction

Roger Girgis, Florian Golemo, Felipe Codevilla, Martin Weiss, Jim Aldon D'Souza, Samira Ebrahimi Kahou, Felix Heide, Christopher Pal

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

Comments 26 pages, 17 figures, 8 tables

2005.01117 2021-12-07 cs.LG cs.AI cs.MA 90%

Multi-agent Reinforcement Learning for Decentralized Stable Matching

Kshitija Taywade, Judy Goldsmith, Brent Harrison

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

Comments 16 pages

Journal ref 7th International Conference on Algorithmic Decision Theory, 2021

2109.06609 2021-09-15 cs.LG cs.AI 90%

DSDF: An approach to handle stochastic agents in collaborative multi-agent reinforcement learning

Satheesh K. Perepu, Kaushik Dey

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

2108.06148 2021-08-16 cs.LG cs.AI 90%

Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments

Vasilii Davydov, Alexey Skrynnik, Konstantin Yakovlev, Aleksandr I. Panov

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

Comments This is a preprint of the paper accepted to RCAI 2021. It contains 11 pages and 5 figures

2105.03546 2021-05-11 cs.MA cs.AI cs.LG cs.RO 90%

Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Colonies

Austin Anhkhoi Nguyen

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

Comments 50 pages, 40 figures

2101.10369 2021-04-02 eess.SP cs.AI cs.IT cs.LG math.IT stat.ML 90%

Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels

Tze-Yang Tung, Szymon Kobus, Joan Roig Pujol, Deniz Gunduz

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

2103.14231 2021-03-29 cs.RO cs.AI cs.CV cs.LG 90%

Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance

Xu Xie, Chi Zhang, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

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

Comments ICRA 2021 paper. Project: https://xuxie1031.github.io/projects/GTA/GTAProj.html

2010.11835 2020-10-24 cs.AI cs.LG cs.MA 90%

Multi-agent active perception with prediction rewards

Mikko Lauri, Frans A. Oliehoek

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

Comments 34th Conference on Neural Information Processing Systems (NeurIPS 2020)

2007.04979 2020-07-10 cs.CV cs.AI cs.LG cs.MA 90%

A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

Unnat Jain, Luca Weihs, Eric Kolve, Ali Farhadi, Svetlana Lazebnik, Aniruddha Kembhavi, Alexander Schwing

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

Comments Accepted to ECCV 2020 (spotlight); Project page: https://unnat.github.io/cordial-sync

2003.11778 2020-07-07 cs.AI cs.LG cs.MA 90%

Too many cooks: Bayesian inference for coordinating multi-agent collaboration

Rose E. Wang, Sarah A. Wu, James A. Evans, Joshua B. Tenenbaum, David C. Parkes, Max Kleiman-Weiner

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

Comments Rose E. Wang and Sarah A. Wu contributed equally

1912.03851 2020-06-30 cs.AI cs.LG cs.MA 90%

Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning

Ujwal Padam Tewari, Vishal Bidawatka, Varsha Raveendran, Vinay Sudhakaran, Shreedhar Kodate Shreeshail, Jayanth Prakash Kulkarni

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

Comments Accepted in the NeurIPS 2019 Deep RL Workshop : https://sites.google.com/view/deep-rl-workshop-neurips-2019/home

2001.10208 2020-01-29 cs.RO cs.AI cs.LG cs.MA 90%

Towards Learning Multi-agent Negotiations via Self-Play

Yichuan Charlie Tang

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

Comments Autonomous Driving Workshop, IEEE International Conference on Computer Vision (ICCV 2019)

1911.04175 2019-11-12 cs.LG cs.AI cs.MA cs.RO stat.ML 90%

Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning

Praveen Palanisamy

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

Comments Accepted, Machine Learning for Autonomous Driving Workshop at the 33rd Conference on Neural Information Processing Systems(NeurIPS 2019)

1904.02390 2019-04-05 cs.RO cs.AI cs.LG 90%

Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning

Jiachen Li, Hengbo Ma, Masayoshi Tomizuka

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

Comments Accepted by 2019 International Conference on Robotics and Automation (ICRA)

1610.03295 2016-10-12 cs.AI cs.LG stat.ML 90%

Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua

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

2608.03339 2026-08-05 cs.AI 新提交 90%

Traceable Multi-Agent System for Knowledge-Based Forecasting

用于基于知识的预测的可追踪多智能体系统

Junhyeok Kang, Sangjun Han, Hyeokjun Choe, Soonyoung Lee

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

AI总结本文提出可追踪多智能体预测演示系统TraceMAS，通过两类因果环图关联证据与预测，在原油价格预测中验证其可让自主智能体兼顾灵活性与过程可检查性。

Comments Accepted at KDD 2026 Workshop on Enterprise AI Agents (Oral)

2606.15931 2026-06-16 cs.MA cs.AI 新提交 90%

DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts

DeepRoot: 一个基于知识图谱协调的多智能体系统，用于历史医学文本的治疗推理

Zijian Carl Ma, Sean J. Wang, Sijbren Kramer, Li Erran Li

机构 * University of California, Berkeley（加州大学伯克利分校）； Stanford University（斯坦福大学）； University of Cambridge（剑桥大学）； University of Toronto（多伦多大学）

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

AI总结提出DeepRoot多智能体系统，通过联合构建和利用验证知识图谱，将接地与推理分离并组合，从历史医学文本中恢复药物-疾病治疗关系，显著优于基线LLM和工具调用LLM。

Journal ref ICML 2026 GenBio; ACM CAIS 2026 Workshop AI Agents for Discovery in the Wild

2604.09618 2026-04-29 cs.DC cs.AI cs.CR 90%

HearthNet: Edge Multi-Agent Orchestration for Smart Homes

HearthNet：边缘多智能体协调用于智能家居

Zhonghao Zhan, Krinos Li, Yefan Zhang, Hamed Haddadi

机构 * Imperial College London（伦敦帝国学院）； Independent Researcher（独立研究员）

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

AI总结 HearthNet通过边缘多智能体系统解决智能家居中自然语言控制、设备故障和持续协调的问题，采用MQTT、Git共享状态和授权租赁实现设备管理。

Comments (CAIS 2026) Proceedings of the ACM Conference on AI and Agentic Systems, Demo Track

2604.06629 2026-04-09 cs.MA cs.AI cs.RO 90%

Logical Robots: Declarative Multi-Agent Programming in Logica

逻辑机器人：逻辑编程中的多智能体编程

Evgeny Skvortsov, Yilin Xia, Ojaswa Garg, Shawn Bowers, Bertram Ludäscher

机构 * Google LLC（谷歌公司）； University of Illinois（伊利诺伊大学）； Gonzaga University（贡扎加大学）

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

AI总结 Logical Robots通过逻辑编程语言Logica实现多智能体仿真平台，将观察映射到动作输出，实现低层反应控制与高层规划的结合。

Comments International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 25-29, 2026. Paphos, Cyprus

2512.10918 2026-03-10 cs.HC cs.CL 90%

CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences

CompanionCast：迈向多智能体系统在共享体验中的社会协作

Yiyang Wang, Chen Chen, Tica Lin, Vishnu Raj, Josh Kimball, Alex Cabral, Josiah Hester

机构 * Georgia Institute of Technology（佐治亚理工学院）； Dolby Laboratories, Inc.（杜比实验室）

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

AI总结 CompanionCast通过多智能体系统提升共享体验中的社会协作，通过多模态检测、上下文缓存和空间音频增强共在感，实验显示其在体育观看中显著提升社会存在感和情感共享。

Comments Accepted at ACM CHI 2026 Workshop on Human-Agent Collaboration

2510.14401 2026-01-28 cs.MA cs.AI 90%

The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systems

在LLM多智能体系统中，社会学习和集体规范形成促进合作的作用

Prateek Gupta, Qiankun Zhong, Hiromu Yakura, Thomas Eisenmann, Iyad Rahwan

机构 * Center for Humans and Machines（人类与机器中心）； Max-Planck Institute for Human Development（人类发展马克斯·普朗克研究所）

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

AI总结本文提出了一种无显式奖励信号的CPR模拟框架，通过社会学习和规范惩罚机制研究LLM多智能体系统中合作与规范的内生形成。

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

2601.00848 2026-01-06 cs.AI cs.CR 90%

Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models

多智能体AI工作流中的时间攻击模式检测：一种用于训练基于轨迹的安全模型的开放框架

Ron F. Del Rosario

机构 * SAP ； OWASP Gen AI Security Project（OWASP生成人工智能安全项目）； Agentic Security Initiative (ASI)（代理安全倡议（ASI））

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

AI总结本文提出了一种开放框架，通过合成轨迹生成和微调语言模型，提升多智能体AI工作流中时间攻击模式检测的准确性，并公开了相关数据集和评估基准。

Comments 26 pages, 3 figures, 7 tables. Datasets and code: https://huggingface.co/guerilla7/agentic-safety-gguf

2510.01751 2025-10-03 cs.AI 90%

A cybersecurity AI agent selection and decision support framework

Masike Malatji

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

Comments 6 figures, 6 tables, AI agents decision support framework

1. 多智能体 14741 篇

Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet

ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning

TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System

MotionLM: Multi-Agent Motion Forecasting as Language Modeling

Probabilistic Symmetry for Multi-Agent Dynamics

Multi-Agent Reinforcement Learning for Long-Term Network Resource Allocation through Auction: a V2X Application

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction

Multi-agent Reinforcement Learning for Decentralized Stable Matching

DSDF: An approach to handle stochastic agents in collaborative multi-agent reinforcement learning

Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments

Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Colonies

Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels

Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance

Multi-agent active perception with prediction rewards

A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

Too many cooks: Bayesian inference for coordinating multi-agent collaboration

Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning

Towards Learning Multi-agent Negotiations via Self-Play

Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning

Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning

Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

Traceable Multi-Agent System for Knowledge-Based Forecasting

DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts

HearthNet: Edge Multi-Agent Orchestration for Smart Homes

Logical Robots: Declarative Multi-Agent Programming in Logica

CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences

The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systems

Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models

A cybersecurity AI agent selection and decision support framework