AI Agent - arXivDaily 专题

2505.22467 2025-10-20 cs.MA cs.AI cs.LG 90%

Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems

Jiaxi Yang, Mengqi Zhang, Yiqiao Jin, Hao Chen, Qingsong Wen, Lu Lin, Yi He, Srijan Kumar, Weijie Xu, James Evans, Jindong Wang

机构 * The Pennsylvania State University（宾夕法尼亚州立大学）； William & Mary（威廉与玛丽学院）； Georgia Institute of Technology（佐治亚理工学院）； AMD（AMD公司）； Squirrel AI ； Amazon（亚马逊公司）； University of Chicago（芝加哥大学）

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

2510.15568 2025-10-20 cs.HC cs.AI 89%

The Spark Effect: On Engineering Creative Diversity in Multi-Agent AI Systems

Alexander Doudkin, Anton Voelker, Friedrich von Borries

机构 * Art of X UG (haftungsbeschraenkt)（Art of X 有限公司）； HFBK Hamburg（汉堡艺术大学）； Hamburg Open Online University (HOOU) program（汉堡开放在线大学（HOOU）计划）

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

Comments 10 pages, 2 figures, 2 tables. This project was collaboratively developed with the Art of X UG (haftungsbeschraenkt) AI Research team and HFBK Hamburg, with initial funding from the Hamburg Open Online University (HOOU) program

2506.07829 2025-10-20 cs.LG cs.AI cs.MA 88%

Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information

Jan Corazza, Hadi Partovi Aria, Hyohun Kim, Daniel Neider, Zhe Xu

机构 * Research Center Trustworthy Data Science and Security of the University Alliance Ruhr（可信数据科学与安全大学联盟鲁尔研究中心）； Department of Computer Science, TU Dortmund University（图腾大学计算机科学系）； Arizona State University（亚利桑那州立大学）

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

Comments Code available at https://github.com/corazza/tcdmarl

Journal ref ECML PKDD 2025 (LNCS, vol. 16018, pp. 77-94)

2510.15682 2025-10-20 cs.IR cs.CL 88%

SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation

Ines Besrour, Jingbo He, Tobias Schreieder, Michael Färber

机构 * TU Dresden（德累斯顿理工大学）

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

Comments Accepted at CIKM 2025

2510.15739 2025-10-20 cs.AI cs.MA 87%

AURA: An Agent Autonomy Risk Assessment Framework

Lorenzo Satta Chiris, Ayush Mishra

机构 * University of Exeter（埃克塞特大学）

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

Comments 10 pages, 2 figures. Submitted for open-access preprint on arXiv. Based on the AAMAS 2026 paper template

2510.15644 2025-10-20 cs.LG eess.SP math.OC 70%

Decentralized Parameter-Free Online Learning

Tomas Ortega, Hamid Jafarkhani

机构 * Center for Pervasive Communications & Computing and EECS Department, University of California, Irvine（普及通信与计算中心及电子工程与计算机科学系，加州大学伊文斯顿分校）

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

2510.15646 2025-10-20 math.AP 67%

Derivation and quasi-invariant asymptotics of phenotype-structured integro-differential models

Emanuele Bernardi, Tommaso Lorenzi, Andrea Tosin

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

2510.15065 2025-10-20 cs.GT 50%

Combinatorial Contract Design: Recent Progress and Emerging Frontiers

Michal Feldman

专题命中多智能体：agent(abstract)

2505.14817 2025-10-20 cs.GT cs.MA 50%

Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles

Kushagra Gupta, Surya Murthy, Mustafa O. Karabag, Ufuk Topcu, David Fridovich-Keil