AI Agent

2510.16394 2025-10-21 eess.IV 50%

FSAR-Cap: A Fine-Grained Two-Stage Annotated Dataset for SAR Image Captioning

Jinqi Zhang, Lamei Zhang, Bin Zou

专题命中规划决策：planning(abstract)

Comments 5pages,4figures

2510.16366 2025-10-21 cs.CY 50%

Integrating LLM and Diffusion-Based Agents for Social Simulation

Xinyi Li, Zhiqiang Guo, Qinglang Guo, Hao Jin, Weizhi Ma, Min Zhang

专题命中规划决策：agent(abstract)

Comments 10 pages, 3 figures, 4 tables

2510.16144 2025-10-21 cs.NI cs.AI cs.MA 91%

Agentic AI for Ultra-Modern Networks: Multi-Agent Framework for RAN Autonomy and Assurance

Sukhdeep Singh, Avinash Bhat, Shweta M, Subhash K Singh, Moonki Hong, Madhan Raj K, Kandeepan Sithamparanathan, Sunder A. Khowaja, Kapal Dev

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

2510.16080 2025-10-21 q-bio.QM cs.AI 89%

TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

Kerem Delikoyun, Qianyu Chen, Win Sen Kuan, John Tshon Yit Soong, Matthew Edward Cove, Oliver Hayden

机构 * Technical University of Munich（慕尼黑技术大学）； National University of Singapore（新加坡国立大学）； National University Hospital（新加坡国立大学医院）

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

2507.16306 2025-10-21 cs.MA cs.RO 89%

COMPASS: Cooperative Multi-Agent Persistent Monitoring using Spatio-Temporal Attention Network

Xingjian Zhang, Yizhuo Wang, Guillaume Sartoretti

机构 * Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore（机械工程系，设计与工程学院，新加坡国立大学）

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

Comments Accepted at IEEE MRS 2025

2510.16645 2025-10-21 cs.CL cs.AI cs.LG cs.MA 89%

Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration

Zhixuan He, Yue Feng

机构 * University of Birmingham, United Kingdom（英国伯明翰大学）

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

2502.08365 2025-10-21 cs.LG cs.AI 88%

Towards Principled Unsupervised Multi-Agent Reinforcement Learning

Riccardo Zamboni, Mirco Mutti, Marcello Restelli

机构 * Politecnico di Milano（米兰理工学院）； Technion（技术学院）

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

2507.22904 2025-10-21 cs.HC cs.AI 88%

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches

Ehsan Latif, Zirak Khan, Xiaoming Zhai

机构 * AI4STEM Education Center University of Georgia（AI4STEM教育中心乔治亚大学）

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

Comments Submitted to NeurIPS2025

2510.16652 2025-10-21 stat.ML cs.LG 88%

ARCO-BO: Adaptive Resource-aware COllaborative Bayesian Optimization for Heterogeneous Multi-Agent Design

Zihan Wang, Yi-Ping Chen, Tuba Dolar, Wei Chen

机构 * Department of Mechanical Engineering, Northwestern University（机械工程系，西北大学）

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

2510.04303 2025-10-21 cs.MA cs.AI 88%

Audit the Whisper: Detecting Steganographic Collusion in Multi-Agent LLMs

Om Tailor

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

Comments 13 pages, 0 figures

2509.24598 2025-10-21 eess.SY cs.SY 88%

Model-Free Dynamic Consensus in Multi-Agent Systems: A Q-Function Perspective

Maryam Babazadeh, Naim Bajcinca

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

2510.16221 2025-10-21 cs.MA cs.SY eess.SY 88%

Heterogeneous Multi-Agent Task-Assignment with Uncertain Execution Times and Preferences

Qinshuang Wei, Vaibhav Srivastava, Vijay Gupta

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

Comments 14 pages

2312.12861 2025-10-21 cs.RO 88%

Safe Multi-Agent Reinforcement Learning for Behavior-Based Cooperative Navigation

Murad Dawood, Sicong Pan, Nils Dengler, Siqi Zhou, Angela P. Schoellig, Maren Bennewitz

机构 * Humanoid Robots Lab, University of Bonn（波恩大学人形机器人实验室）

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

2510.16572 2025-10-21 cs.AI cs.MA 83%

Ripple Effect Protocol: Coordinating Agent Populations

Ayush Chopra, Aman Sharma, Feroz Ahmad, Luca Muscariello, Vijoy Pandey, Ramesh Raskar

机构 * Massachusetts Institute of Technology（麻省理工学院）； Project Iceberg ； Cisco（思科）

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

2510.10381 2025-10-21 physics.soc-ph nlin.AO 82%

Quantifying Emergent Behaviors in Agent-Based Models using Mean Information Gain

Sebastián Rodríguez-Falcón, Luciano Stucchi

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

Comments 5 pages, 4 figures

2510.16996 2025-10-21 cs.AI 81%

STARK: Strategic Team of Agents for Refining Kernels

Juncheng Dong, Yang Yang, Tao Liu, Yang Wang, Feng Qi, Vahid Tarokh, Kaushik Rangadurai, Shuang Yang

机构 * Meta Ranking AI Research（Meta 排名人工智能研究）； Duke University（杜克大学）

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

2504.01234 2025-10-21 cs.MA physics.optics 78%

First Field-Trial Demonstration of L4 Autonomous Optical Network for Distributed AI Training Communication: An LLM-Powered Multi-AI-Agent Solution

Yihao Zhang, Qizhi Qiu, Xiaomin Liu, Dianxuan Fu, Xingyu Liu, Leyan Fei, Yuming Cheng, Lilin Yi, Weisheng Hu, Qunbi Zhuge

专题命中多智能体：agent(title,abstract)

Comments Accepted by 51st European Conference on Optical Communication (ECOC 2025), paper W.02.01.177

2506.21974 2025-10-21 cs.CL 70%

Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism

Simon Münker, Nils Schwager, Achim Rettinger

机构 * Trier University（特里尔大学）

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

Comments 11 pages, 1 figure, 3 tables

2408.01072 2025-10-21 cs.AI 70%

A Survey on Self-play Methods in Reinforcement Learning

Ruize Zhang, Zelai Xu, Chengdong Ma, Chao Yu, Wei-Wei Tu, Wenhao Tang, Shiyu Huang, Deheng Ye, Wenbo Ding, Yaodong Yang, Yu Wang

机构 * Tsinghua University（清华大学）； Peking University（北京大学）； Tencent（腾讯）

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

2510.17603 2025-10-21 cs.CV 67%

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

Shuyuan Zhang, Chenhan Jiang, Zuoou Li, Jiankang Deng

机构 * Imperial College London（伦敦帝国学院）； Hong Kong University of Science and Technology（香港科学与技术大学）

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

Comments NeurIPS 2025 Poster

2510.16402 2025-10-21 cs.LO 67%

Explainability Requirements as Hyperproperties

Bernd Finkbeiner, Julian Siber

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

Journal ref Acta Informatica 62, 38 (2025)

2504.06557 2025-10-21 econ.TH cs.SI physics.soc-ph 67%

Market, power, gift, and concession economies: Comparison using four-mode primitive network models

Takeshi Kato, Junichi Miyakoshi, Misa Owa, Ryuji Mine

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

Comments 28 pages, 5 figures

Journal ref PLoS One 20(8): e0330174 (2025)

2502.01506 2025-10-21 cs.CE cs.CY 67%

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets

Yuzhe Yang, Yifei Zhang, Minghao Wu, Kaidi Zhang, Yunmiao Zhang, Honghai Yu, Yan Hu, Benyou Wang

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

2510.16844 2025-10-21 cs.CL cs.AI cs.CE 62%

FinSight: Towards Real-World Financial Deep Research

Jiajie Jin, Yuyao Zhang, Yimeng Xu, Hongjin Qian, Yutao Zhu, Zhicheng Dou

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学耿丽人工智能学院）； BAAI（北京人工智能研究院）

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

Comments Working in progress

2510.17301 2025-10-21 cs.DB cs.AI 57%

Comprehending Spatio-temporal Data via Cinematic Storytelling using Large Language Models

Panos Kalnis. Shuo Shang, Christian S. Jensen

机构 * King Abdullah University of Science and Technology (KAUST)（卡塔尔国王 Abdullah 科学与技术大学）； University of Electronic Science and Technology of China (UESTC)（中国电子科学与技术大学）； Aalborg University（奥尔堡大学）

专题命中多智能体：agent(abstract)；分类 cs.AI

Comments 5 pages

Journal ref SSTD '25: Proceedings of the 19th International Symposium on Spatial and Temporal Data, Pages 12,26, 2025

2510.17036 2025-10-21 cs.LG 57%

Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation

Nguyen Do, Bach Ngo, Youval Kashuv, Canh V. Pham, Hanghang Tong, My T. Thai

机构 * University of Florida, FL, USA（佛罗里达大学）； The Frazer School, FL, USA（弗雷泽学校）； ORLab, Phenikaa University, Viet Nam（Phenikaa大学OR实验室）； University of Illinois at Urbana-Champaign, IL, USA（伊利诺伊大学厄巴纳-香槟分校）

专题命中多智能体：agent(abstract)；分类 cs.LG

Comments 62 pages, 19 figures, Neural Information Processing Systems (NeurIPS 2025)

2510.17769 2025-10-21 eess.SY cs.SY 50%

Data-driven Communication and Control Design for Distributed Frequency Regulation with Black-box Inverters

Michael Nestor, Jiaxin Wang, Ning Zhang, Fei Teng

专题命中多智能体：agent(abstract)

Comments Preprint submitted to PSCC 2026

2510.17617 2025-10-21 cs.HC cs.CV 50%

ImaGGen: Zero-Shot Generation of Co-Speech Semantic Gestures Grounded in Language and Image Input

Hendric Voss, Stefan Kopp

机构 * Social Cognitive Systems Group, Bielefeld University（比勒菲尔德大学社会认知系统小组）

专题命中多智能体：agent(abstract)

2504.04475 2025-10-21 eess.SY cs.SY 50%

Nash equilibrium seeking in coalition games for multiple Euler-Lagrange systems: Analysis and application to USV swarm confrontation

Cheng Yuwen, Jialing Zhou, Meng Luan, Guanghui Wen, Tingwen Huang

专题命中多智能体：agent(abstract)

2510.16872 2025-10-21 cs.AI cs.CL cs.DB 84%

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Shaolei Zhang, Ju Fan, Meihao Fan, Guoliang Li, Xiaoyong Du

机构 * ruc（中国人民大学）； tsinghua（清华大学）

专题命中工作流自动化：agentic(title,abstract)；workflow(abstract)；分类 cs.AI、cs.CL

Comments Code: https://github.com/ruc-datalab/DeepAnalyze Model: https://huggingface.co/RUC-DataLab/DeepAnalyze-8B

1. 规划决策 55 篇

FSAR-Cap: A Fine-Grained Two-Stage Annotated Dataset for SAR Image Captioning

Integrating LLM and Diffusion-Based Agents for Social Simulation

2. 多智能体 27 篇

Agentic AI for Ultra-Modern Networks: Multi-Agent Framework for RAN Autonomy and Assurance

TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

COMPASS: Cooperative Multi-Agent Persistent Monitoring using Spatio-Temporal Attention Network

Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration

Towards Principled Unsupervised Multi-Agent Reinforcement Learning

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches

ARCO-BO: Adaptive Resource-aware COllaborative Bayesian Optimization for Heterogeneous Multi-Agent Design

Audit the Whisper: Detecting Steganographic Collusion in Multi-Agent LLMs

Model-Free Dynamic Consensus in Multi-Agent Systems: A Q-Function Perspective

Heterogeneous Multi-Agent Task-Assignment with Uncertain Execution Times and Preferences

Safe Multi-Agent Reinforcement Learning for Behavior-Based Cooperative Navigation

Ripple Effect Protocol: Coordinating Agent Populations

Quantifying Emergent Behaviors in Agent-Based Models using Mean Information Gain

STARK: Strategic Team of Agents for Refining Kernels

First Field-Trial Demonstration of L4 Autonomous Optical Network for Distributed AI Training Communication: An LLM-Powered Multi-AI-Agent Solution

Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism

A Survey on Self-play Methods in Reinforcement Learning

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

Explainability Requirements as Hyperproperties

Market, power, gift, and concession economies: Comparison using four-mode primitive network models

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets

FinSight: Towards Real-World Financial Deep Research

Comprehending Spatio-temporal Data via Cinematic Storytelling using Large Language Models

Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation

Data-driven Communication and Control Design for Distributed Frequency Regulation with Black-box Inverters

ImaGGen: Zero-Shot Generation of Co-Speech Semantic Gestures Grounded in Language and Image Input

Nash equilibrium seeking in coalition games for multiple Euler-Lagrange systems: Analysis and application to USV swarm confrontation

3. 工作流自动化 19 篇

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science