AI Agent - arXivDaily 专题

2507.21969 2025-07-30 cs.MA 88%

Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation

Adam Kostka, Jarosław A. Chudziak

专题命中 Agent评测：agent(title,abstract)；multi-agent(title,abstract)

Comments Accepted at CogSci 2025

2507.21113 2025-07-30 cs.CR 82%

Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Farzana Abdulzada

专题命中 Agent评测：agent(title,abstract)；planning(abstract)

2507.21188 2025-07-30 cs.LG cs.AI 81%

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs

Raj Krishnan Vijayaraj

机构 * Independent Researcher（独立研究者）

专题命中 Agent评测：agentic(title,abstract)；分类 cs.AI、cs.LG

2507.22049 2025-07-30 cs.MA 78%

Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions

Logan Cross, Nick Haber, Daniel L. K. Yamins

专题命中 Agent评测：agent(title,abstract)

2507.21724 2025-07-30 cs.MA 78%

Agent-Based Exploration of Recommendation Systems in Misinformation Propagation

Lise Jakobsen, Anna Johanne Holden, Önder Gürcan, Özlem Özgöbek

专题命中 Agent评测：agent(title,abstract)

Comments 14 pages, 3 figures, Social Simulation Conference 2025 (SSC'2025)

2507.21547 2025-07-30 math.OC cs.RO cs.SY eess.SY 75%

Decentralized Modeling of Vehicular Maneuvers and Interactions at Urban Junctions

Saeed Rahmani, Simeon C. Calvert, Bart van Arem

机构 * Delft University of Technology（代尔夫特理工大学）

专题命中 Agent评测：agent(abstract)；planning(abstract)；multi-agent(abstract)

Comments Manuscript under review

2507.21631 2025-07-30 cs.AI cs.MA 70%

"Teammates, Am I Clear?": Analysing Legible Behaviours in Teams

Miguel Faria, Francisco S. Melo, Ana Paiva

机构 * SARDINE ； Instituto de Telecomunicações（电信研究所）； Instituto Superior Técnico（技术高等学院）； INESC-ID（葡萄牙创新科学与技术研究所）

专题命中 Agent评测：agent(abstract)；multi-agent(abstract)；分类 cs.AI

2507.21385 2025-07-30 cs.NI cs.AI 70%

Deep Reinforcement Learning-based Cell DTX/DRX Configuration for Network Energy Saving

Wei Mao, Lili Wei, Omid Semiari, Shu-ping Yeh, Hosein Nikopour

专题命中 Agent评测：agent(abstract)；AI agent(abstract)；分类 cs.AI

Comments 7 pages, 7 figures

2406.14540 2025-07-30 cs.RO cs.AI cs.CV 70%

IRASim: A Fine-Grained World Model for Robot Manipulation

Fangqi Zhu, Hongtao Wu, Song Guo, Yuxiao Liu, Chilam Cheang, Tao Kong

机构 * Hong Kong University of Science and Technology（香港科技大学）； ByteDance Seed（字节跳动种子）

专题命中 Agent评测：autonomous agent(abstract)；planning(abstract)；分类 cs.AI

Comments Opensource, project website: https://gen-irasim.github.io

Journal ref ICCV 2025

2507.22034 2025-07-30 cs.AI cs.CL cs.LG 67%

UserBench: An Interactive Gym Environment for User-Centric Agents

Cheng Qian, Zuxin Liu, Akshara Prabhakar, Zhiwei Liu, Jianguo Zhang, Haolin Chen, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang

机构 * Salesforce AI Research（Salesforce AI研究部）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

专题命中 Agent评测：tool use(abstract)；分类 cs.AI、cs.CL、cs.LG

Comments 25 Pages, 17 Figures, 6 Tables

2507.21504 2025-07-30 cs.LG cs.AI 62%

Evaluation and Benchmarking of LLM Agents: A Survey

Mahmoud Mohammadi, Yipeng Li, Jane Lo, Wendy Yip

机构 * SAP Labs（SAP实验室）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2507.21196 2025-07-30 cs.LG cs.AI 62%

EdgeAgentX-DT: Integrating Digital Twins and Generative AI for Resilient Edge Intelligence in Tactical Networks

Abir Ray

机构 * Cornell University（康奈尔大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 13 pages, 6 figures

2505.11135 2025-07-30 cs.AI cs.LG cs.NE 62%

Scalability of Reinforcement Learning Methods for Dispatching in Semiconductor Frontend Fabs: A Comparison of Open-Source Models with Real Industry Datasets

Patrick Stöckermann, Henning Südfeld, Alessandro Immordino, Thomas Altenmüller, Marc Wegmann, Martin Gebser, Konstantin Schekotihin, Georg Seidel, Chew Wye Chan, Fei Fei Zhang

机构 * Infineon Technologies AG（英飞凌科技有限公司）； University of Klagenfurt（克雷格福尔特大学）； Technical University Munich（慕尼黑技术大学）； University of Padua（帕多瓦大学）； D-SIMLAB Technologies Pte Ltd（D-SIMLAB技术私人有限公司）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2505.20726 2025-07-30 cs.RO 50%

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making

Liu Dai, Haina Wang, Weikang Wan, Hao Su

专题命中 Agent评测：agent(abstract)

Comments Project Website: https://manitaskgen.github.io/

2002.10898 2025-07-30 cs.GT cs.CC cs.DS 50%

Hedonic Seat Arrangement Problems

Hans L. Bodlaender, Tesshu Hanaka, Lars Jaffke, Hirotaka Ono, Yota Otachi, Tom C. van der Zanden

专题命中 Agent评测：agent(abstract)

1. Agent评测 15 篇

Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation

Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs

Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions

Agent-Based Exploration of Recommendation Systems in Misinformation Propagation

Decentralized Modeling of Vehicular Maneuvers and Interactions at Urban Junctions

"Teammates, Am I Clear?": Analysing Legible Behaviours in Teams

Deep Reinforcement Learning-based Cell DTX/DRX Configuration for Network Energy Saving

IRASim: A Fine-Grained World Model for Robot Manipulation

UserBench: An Interactive Gym Environment for User-Centric Agents

Evaluation and Benchmarking of LLM Agents: A Survey

EdgeAgentX-DT: Integrating Digital Twins and Generative AI for Resilient Edge Intelligence in Tactical Networks

Scalability of Reinforcement Learning Methods for Dispatching in Semiconductor Frontend Fabs: A Comparison of Open-Source Models with Real Industry Datasets

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making

Hedonic Seat Arrangement Problems