AI Agent - arXivDaily 专题

2503.23615 2025-04-01 cs.AI cs.LG 88%

An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning

Julien Soulé, Jean-Paul Jamont, Michel Occello, Louis-Marie Traonouez, Paul Théron

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

2503.21200 2025-03-31 cs.LG cs.AI cs.MA 88%

Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

Sicong Liu, Yang Shu, Chenjuan Guo, Bin Yang

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

2503.21807 2025-03-31 cs.LG cs.AI cs.MA 88%

LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning

Yuan Wei, Xiaohan Shan, Jianmin Li

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

2405.16439 2025-03-28 cs.RO cs.AI cs.LG cs.MA 88%

Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds

Rohan Chandra, Haresh Karnan, Negar Mehr, Peter Stone, Joydeep Biswas

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

2405.12236 2025-03-27 cs.AI cs.DC cs.LG cs.MA 88%

Fully Distributed Fog Load Balancing with Multi-Agent Reinforcement Learning

Maad Ebrahim, Abdelhakim Hafid

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

Comments Submitted to IEEE TNSM with 14 pages, 11 figures, and 3 tables

2503.18891 2025-03-25 cs.CL cs.AI 88%

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration

Zhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding, Miao Zhang, Jie Liu, Min Zhang

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

2503.17803 2025-03-25 cs.LG cs.AI cs.MA stat.ME 88%

A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference

Giovanni Briglia, Stefano Mariani, Franco Zambonelli

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

2503.15272 2025-03-20 cs.CL cs.AI 88%

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration

David Wan, Justin Chih-Yao Chen, Elias Stengel-Eskin, Mohit Bansal

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

Comments NAACL 2025, 18 pages. Code: https://github.com/meetdavidwan/mammrefine

2503.15204 2025-03-20 cs.HC cs.AI cs.CL cs.IR cs.MA 88%

When Pigs Get Sick: Multi-Agent AI for Swine Disease Detection

Tittaya Mairittha, Tanakon Sawanglok, Panuwit Raden, Sorrawit Treesuk

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

Comments 14 pages, 2 figures

2503.15172 2025-03-20 cs.LG cs.AI cs.NI 88%

Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems

George Stamatelis, Angelos-Nikolaos Kanatas, George C. Alexandropoulos

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

Comments 5 pages, 3 figures, 1 table, submited to an IEEE conference

2411.06601 2025-03-19 cs.AI cs.LG cs.MA 88%

OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control

Rohit Bokade, Xiaoning Jin

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

2503.11726 2025-03-18 cs.LG cs.AI 88%

SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks

Hyunwoo Park, Baekryun Seong, Sang-Ki Ko

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

Comments 31 pages, 14 figures

2503.11517 2025-03-17 cs.AI cs.CL cs.MA 88%

Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks

Diego Gosmar, Deborah A. Dahl, Dario Gosmar

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

Comments 22 pages, 9 figures

2503.04817 2025-03-10 cs.CL cs.AI cs.MA cs.MM 88%

Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series

Roberto Balestri, Guglielmo Pescatore

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

Comments 17th International Conference on Agents and Artificial Intelligence, Porto (Portugal). 23/02/2025 - 25/02/2025

Journal ref 2025. Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1, ISBN 978-989-758-737-5, ISSN 2184-433X, pages 663-670

2503.03796 2025-03-10 cs.MA cs.AI cs.LG cs.RO 88%

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm

Hyeonjun Kim, Kanghoon Lee, Junho Park, Jiachen Li, Jinkyoo Park

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

Comments 7 pages, 4 figures

2503.04679 2025-03-07 cs.MA cs.AI cs.LG cs.RO 88%

Multi-Agent Inverse Q-Learning from Demonstrations

Nathaniel Haynam, Adam Khoja, Dhruv Kumar, Vivek Myers, Erdem Bıyık

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

Comments 8 pages, 4 figures, 2 tables. Published at the International Conference on Robotics and Automation (ICRA) 2025

2403.11807 2025-03-07 cs.AI cs.CL 88%

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments

Jen-tse Huang, Eric John Li, Man Ho Lam, Tian Liang, Wenxuan Wang, Youliang Yuan, Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Michael R. Lyu

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

Comments Accepted to ICLR 2025; 11 pages of main text; 26 pages of appendices; Included models: GPT-3.5-{0613, 1106, 0125}, GPT-4-0125, GPT-4o-0806, Gemini-{1.0, 1.5)-Pro, LLaMA-3.1-{7, 70, 405}B, Mixtral-8x{7, 22}B, Qwen-2-72B

2411.00053 2025-03-07 cs.CL cs.AI 88%

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu

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

2404.05569 2025-03-07 cs.AI cs.CL cs.MA 88%

360$^\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System

Shen Gao, Hao Li, Chengrui Huang, Quan Tu, Zhiliang Tian, Minlie Huang, Shuo Shang

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

2503.02954 2025-03-06 cs.RO cs.AI cs.LG cs.MA 88%

Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders

Yue Meng, Nathalie Majcherczyk, Wenliang Liu, Scott Kiesel, Chuchu Fan, Federico Pecora

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

Comments Accepted by 2025 International Conference on Robotics and Automation (ICRA 2025)

2503.01458 2025-03-04 cs.AI cs.LG cs.MA 88%

SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning

Xu Wan, Chao Yang, Cheng Yang, Jie Song, Mingyang Sun

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

2503.00684 2025-03-04 cs.MA cs.AI cs.LG cs.RO 88%

Factorized Deep Q-Network for Cooperative Multi-Agent Reinforcement Learning in Victim Tagging

Maria Ana Cardei, Afsaneh Doryab

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

Comments This work has been submitted to the IEEE for possible publication

2410.07672 2025-03-04 cs.CL cs.AI 88%

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

Yougang Lyu, Lingyong Yan, Zihan Wang, Dawei Yin, Pengjie Ren, Maarten de Rijke, Zhaochun Ren

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

Comments ICLR 2025

2503.00355 2025-03-04 cs.CL cs.AI 88%

Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data

Tianyi Huang, Elsa Fan

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

Comments Accepted Paper (Oral Presentation) in the Workshop on the Social Impact of AI: Research, Diversity and Inclusion Frameworks at AAAI 2025

2503.00162 2025-03-04 cs.CV cs.AI cs.CL cs.MA 88%

PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos

Kangda Wei, Zhengyu Zhou, Bingqing Wang, Jun Araki, Lukas Lange, Ruihong Huang, Zhe Feng

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

2406.01782 2025-03-03 eess.SY cs.AI cs.LG cs.MA cs.SY 88%

Multi-agent assignment via state augmented reinforcement learning

Leopoldo Agorio, Sean Van Alen, Miguel Calvo-Fullana, Santiago Paternain, Juan Andres Bazerque

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

Comments 12 pages, 3 figures, 6th Annual Conference on Learning for Dynamics and Control

Journal ref Proceedings of Machine Learning Research vol 242 1 12, 2024. 6th Annual Conference on Learning for Dynamics and Control

2502.16128 2025-02-28 cs.LG cs.AI cs.GT cs.MA 88%

Heterogeneous Multi-Agent Bandits with Parsimonious Hints

Amirmahdi Mirfakhar, Xuchuang Wang, Jinhang Zuo, Yair Zick, Mohammad Hajiesmaili

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

Comments Accepted at AAAI-2025

2502.18653 2025-02-27 cs.CL cs.AI 88%

Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT

Hediyeh Baban, Sai A Pidapar, Aashutosh Nema, Sichen Lu

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

2502.16496 2025-02-25 cs.LG cs.AI cs.MA 88%

PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning

Kun Hu, Muning Wen, Xihuai Wang, Shao Zhang, Yiwei Shi, Minne Li, Minglong Li, Ying Wen

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

Comments Accepted by AAMAS 2025

2502.15700 2025-02-25 cs.IR cs.AI cs.CL 88%

Sustainable Digitalization of Business with Multi-Agent RAG and LLM

Muhammad Arslan, Saba Munawar, Christophe Cruz

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

1. 多智能体 14795 篇

An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning

Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning

Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds

Fully Distributed Fog Load Balancing with Multi-Agent Reinforcement Learning

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration

A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration

When Pigs Get Sick: Multi-Agent AI for Swine Disease Detection

Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems

OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control

SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks

Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks

Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm

Multi-Agent Inverse Q-Learning from Demonstrations

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

360$^\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System

Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders

SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning

Factorized Deep Q-Network for Cooperative Multi-Agent Reinforcement Learning in Victim Tagging

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data

PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos

Multi-agent assignment via state augmented reinforcement learning

Heterogeneous Multi-Agent Bandits with Parsimonious Hints

Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT

PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning

Sustainable Digitalization of Business with Multi-Agent RAG and LLM