AI Agent

2409.06345 2025-10-16 cs.MA 82%

Foragax: An Agent-Based Modelling Framework Based on JAX

Siddharth Chaturvedi, Ahmed El-Gazzar, Marcel van Gerven

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

Comments A new version of the framework with more complete features is available in the form of ABMax (arXiv:2508.16508)

2505.04364 2025-10-16 cs.MA cs.CL 77%

Benchmarking LLMs' Swarm intelligence

Kai Ruan, Mowen Huang, Ji-Rong Wen, Hao Sun

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（人工智能学院，中国人民大学）

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

2411.11057 2025-10-16 cs.AI 77%

Reinforcing Competitive Multi-Agents for Playing 'So Long Sucker'

Medant Sharan, Chandranath Adak

机构 * Dept. of Informatics, King's College London（信息学院，伦敦国王学院）； Dept. of CSE, Indian Institute of Technology Patna（计算机科学与工程系，印度理工学院帕纳布）

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

2510.12920 2025-10-16 astro-ph.IM cs.AI 70%

InferA: A Smart Assistant for Cosmological Ensemble Data

Justin Z. Tam, Pascal Grosset, Divya Banesh, Nesar Ramachandra, Terece L. Turton, James Ahrens

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

2504.04160 2025-10-16 cs.LG cs.MA 70%

OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning

Alexandre Oliveira, Katarina Dyreby, Francisco Caldas, Cláudia Soares

机构 * NOVA LINCS

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

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

2410.16566 2025-10-16 cs.GT cs.CY 67%

Revenue vs. Welfare: A Comprehensive Analysis of Strategic Trade-offs in Online Food Delivery Systems

Yukun Zhang, Qi Dong

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

Journal ref International Conference on AI and the Digital Economy (CADE 2025)

2510.12825 2025-10-16 cs.CL cs.AI cs.DB cs.LG 85%

Classifier-Augmented Generation for Structured Workflow Prediction

Thomas Gschwind, Shramona Chakraborty, Nitin Gupta, Sameep Mehta

机构 * IBM Research（IBM研究院）

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

Comments Accepted at EMNLP 2025

2510.13248 2025-10-16 cs.NI cs.LG 77%

Automated Network Protocol Testing with LLM Agents

Yunze Wei, Kaiwen Wei, Shibo Du, Jianyu Wang, Zhangzhong Liu, Yawen Wang, Zhanyou Li, Congcong Miao, Xiaohui Xie, Yong Cui

机构 * Tsinghua University（清华大学）； Beijing Xinertel Technology Co., Ltd.（北京新ertel技术有限公司）； Tencent（腾讯）

专题命中工作流自动化：agent(abstract)；workflow(abstract)；multi-agent(abstract)；分类 cs.LG

2510.13300 2025-10-16 physics.med-ph 67%

Five Years of Clinical Application of independent Monte Carlo-Based Patient-Specific Quality Assurance at the Maastro Proton Therapy Center

Ilaria Rinaldi, Giorgio Cartechini, Angelo Schiavi, Jan Gajewski, Nils Krah, Antoni Rucinski, Gloria Vilches Freixas, Vincenzo Patera, Sebastiaan Nijsten

专题命中工作流自动化：planning(abstract)；workflow(abstract)

2510.13792 2025-10-16 cs.LG cs.AI 62%

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach

Ziqing Lu, Lifeng Lai, Weiyu Xu

机构 * University of Iowa（爱荷华大学）； University of California, Davis（加州大学戴维斯分校）

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

2510.12835 2025-10-16 cs.CL cs.AI 62%

Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study

Kon Woo Kim, Rezarta Islamaj, Jin-Dong Kim, Florian Boudin, Akiko Aizawa

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

Comments 11 pages, 2 figures, 3 tables, This is a preprint of the article accepted at NLDB 2025 (Springer LNCS). The final version is available at https://doi.org/10.1007/978-3-031-97144-0_13

Journal ref In International Conference on Applications of Natural Language to Information Systems, pp. 140-151. Cham: Springer Nature Switzerland, 2025

2506.19622 2025-10-16 cs.RO cs.FL cs.SE cs.SY eess.SY 57%

A Verification Methodology for Safety Assurance of Robotic Autonomous Systems

Mustafa Adam, David A. Anisi, Pedro Ribeiro

机构 * Faculty of Science and Technology, Norwegian University Of Life Sciences (NMBU)（科学与技术学院，挪威生命科学大学）； Department of Mechatronics, University of Agder (UiA)（机械电子系，阿格德大学）； Department of Computer Science, University Of York, UK（计算机科学系，约克大学（英国））

专题命中工作流自动化：workflow(abstract)；分类 cs.SE

Comments In Proc. of the 26th TAROS (Towards Autonomous Robotic Systems) Conference, York, UK, August, 2025

2505.03622 2025-10-16 physics.app-ph cond-mat.mes-hall 50%

Direct integration of atomic precision advanced manufacturing into middle-of-line silicon fabrication

E. M. Anderson, C. R. Allemang, A. J. Leenheer, S. W. Schmucker, J. A. Ivie, D. M. Campbell, W. Lepkowski, X. Gao, P. Lu, C. Arose, T. -M. Lu, C. Halsey, T. D. England, D. R. Ward, D. A. Scrymgeour, S. Misra

专题命中工作流自动化：workflow(abstract)

Comments This article has been published by Applied Physics Reviews at https://pubs.aip.org/aip/apr/article/12/4/041402/3366930/Direct-integration-of-atomic-precision-advanced as part of Special Collection: Advances on Manufacturing and Next-generation Devices Towards CHIPS Act https://pubs.aip.org/apr/collection/433328/Advances-on-Manufacturing-and-Next-generation. Copyright 2025 Authors

Journal ref Applied Physics Reviews, 12, 041402 (2025)

2510.12864 2025-10-16 cs.AI cs.CL cs.LG 80%

From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language Models

Imran Khan

机构 * Independent Researcher（独立研究者）

专题命中软件智能体：AI agent(abstract)；autonomous agent(abstract)；agentic(abstract)；分类 cs.AI、cs.CL、cs.LG

Comments 13 pages. Code and data are available at https://github.com/strongSoda/LITERAL-TO-LIBERAL

2510.13081 2025-10-16 cs.MA cs.AI 74%

Agentic Discovery: Closing the Loop with Cooperative Agents

J. Gregory Pauloski, Kyle Chard, Ian T. Foster

机构 * University of Chicago（芝加哥大学）； Argonne National Laboratory（阿贡国家实验室）

专题命中软件智能体：agentic(title)；分类 cs.AI

Comments Published in IEEE Computer Volume 58 Issue 10

2510.13543 2025-10-16 cs.CR cs.AI 85%

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Avihay Cohen

机构 * Avihay Cohen

专题命中 GUI与网页智能体：agentic(title,abstract)；agent(abstract)；AI agent(abstract)；分类 cs.AI

Comments 37 pages , 10 figures

2509.01052 2025-10-16 cs.AI cs.CL cs.CV 62%

FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

Jaewoo Ahn, Junseo Kim, Heeseung Yun, Jaehyeon Son, Dongmin Park, Jaewoong Cho, Gunhee Kim

机构 * Seoul National University（首尔国立大学）； KRAFTON ； Georgia Institute of Technology（佐治亚理工学院）

专题命中 GUI与网页智能体：agentic(abstract)；分类 cs.AI、cs.CL

Comments EMNLP 2025 Main. Project page: https://ahnjaewoo.github.io/flashadventure

2505.07008 2025-10-16 cs.GT cs.MA 75%

Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria

Fengming Zhu, Fangzhen Lin

专题命中记忆与上下文管理：agent(abstract)；planning(abstract)；multi-agent(abstract)

Comments 21 pages. Under review

2510.13366 2025-10-16 cs.CL cs.AI 62%

Document Intelligence in the Era of Large Language Models: A Survey

Weishi Wang, Hengchang Hu, Zhijie Zhang, Zhaochen Li, Hongxin Shao, Daniel Dahlmeier

机构 * SAP, Singapore（新加坡SAP）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.CL

2510.13363 2025-10-16 cs.CL 57%

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree

Xiang Lei, Qin Li, Min Zhang, Min Zhang

专题命中记忆与上下文管理：agentic(abstract)；分类 cs.CL

Comments 8 pages, 6 figures (main content); 25 pages, 18 figures (total)

2510.13371 2025-10-16 cs.IR cs.AI 79%

MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation

Jiin Park, Misuk Kim

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

Comments 18 pages

2403.16843 2025-10-16 cs.LG cs.AI cs.GT 79%

Do LLM Agents Have Regret? A Case Study in Online Learning and Games

Chanwoo Park, Xiangyu Liu, Asuman Ozdaglar, Kaiqing Zhang

机构 * Massachusetts Institute of Technology（麻省理工学院）； University of Maryland, College Park（马里兰大学College Park分校）

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

Comments Camera ready version of ICLR 2025

2502.03207 2025-10-16 cs.CV cs.GR 78%

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

Xinyao Liao, Xianfang Zeng, Liao Wang, Gang Yu, Guosheng Lin, Chi Zhang

机构 * Nanyang Technological University（南洋理工大学）； StepFun ； Westlake University（西湖大学）

专题命中 Agent评测：agent(title,abstract)

2510.09558 2025-10-16 cs.CL 70%

AutoPR: Let's Automate Your Academic Promotion!

Qiguang Chen, Zheng Yan, Mingda Yang, Libo Qin, Yixin Yuan, Hanjing Li, Jinhao Liu, Yiyan Ji, Dengyun Peng, Jiannan Guan, Mengkang Hu, Yantao Du, Wanxiang Che

机构 * LARG ； Research Center for Social Computing and Interactive Robotics（社会计算与交互机器人研究室）； Harbin Institute of Technology（哈尔滨工业大学）； School of Computer Science and Engineering（计算机科学与工程学院）； Central South University（中南大学）； The University of Hong Kong（香港大学）； ByteDance China (Seed)（字节跳动中国（种子））

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

Comments Preprint. Code: https://github.com/LightChen233/AutoPR . Benchmark: https://huggingface.co/datasets/yzweak/PRBench

2505.16902 2025-10-16 cs.CV cs.RO 67%

RealEngine: Simulating Autonomous Driving in Realistic Context

Junzhe Jiang, Nan Song, Jingyu Li, Xiatian Zhu, Li Zhang

机构 * School of Data Science, Fudan University（复旦大学数据科学学院）； University of Surrey（萨里大学）

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

2510.13052 2025-10-16 cs.LG cs.AI cs.SY eess.SP eess.SY math.OC 62%

Time-Varying Optimization for Streaming Data Via Temporal Weighting

Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson

机构 * School of Electrical, Computer and Energy Engineering, Arizona State University（亚利桑那州立大学电气、计算机与能源工程学院）； Department of Electrical Engineering (ISY), Linköping University（利尔贝里大学电气工程系）

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

Comments Accepted at IEEE Asilomar, 2025

2501.01540 2025-10-16 cs.LG cs.AI 62%

BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery

Kanishk Gandhi, Michael Y. Li, Lyle Goodyear, Agam Bhatia, Louise Li, Aditi Bhaskar, Mohammed Zaman, Noah D. Goodman

机构 * Stanford University（斯坦福大学）

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

Comments KG and MYL contributed equally

2510.13557 2025-10-16 cs.CV cs.AI 61%

Modeling Cultural Bias in Facial Expression Recognition with Adaptive Agents

David Freire-Obregón, José Salas-Cáceres, Javier Lorenzo-Navarro, Oliverio J. Santana, Daniel Hernández-Sosa, Modesto Castrillón-Santana

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

Comments Accepted for presentation at the International Symposium on Agentic Artificial Intelligence Systems (AAIS 2025)

2510.13395 2025-10-16 cs.CL 57%

Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models

Agnese Lombardi, Alessandro Lenci

机构 * CoLing Lab, Department of Philology, Literature and Linguistics, University of Pisa（帕尔马大学哲学、文学与语言学系语言实验室）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Journal ref roceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)

2111.02310 2025-10-16 math.OC 50%

Nash equilibria for relative investors via no-arbitrage arguments

Nicole Bäuerle, Tamara Göll

专题命中 Agent评测：agent(abstract)

Comments 17 pages

Journal ref Mathematical Methods of Operations Research 97, 1-23 (2023)

1. 多智能体 9 篇

Foragax: An Agent-Based Modelling Framework Based on JAX

Benchmarking LLMs' Swarm intelligence

Reinforcing Competitive Multi-Agents for Playing 'So Long Sucker'

InferA: A Smart Assistant for Cosmological Ensemble Data

OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning

Revenue vs. Welfare: A Comprehensive Analysis of Strategic Trade-offs in Online Food Delivery Systems

2. 工作流自动化 7 篇

Classifier-Augmented Generation for Structured Workflow Prediction

Automated Network Protocol Testing with LLM Agents

Five Years of Clinical Application of independent Monte Carlo-Based Patient-Specific Quality Assurance at the Maastro Proton Therapy Center

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach

Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study

A Verification Methodology for Safety Assurance of Robotic Autonomous Systems

Direct integration of atomic precision advanced manufacturing into middle-of-line silicon fabrication

3. 软件智能体 2 篇

From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language Models

Agentic Discovery: Closing the Loop with Cooperative Agents

4. GUI与网页智能体 2 篇

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

5. 记忆与上下文管理 3 篇

Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria

Document Intelligence in the Era of Large Language Models: A Survey

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree

6. Agent评测 15 篇

MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation

Do LLM Agents Have Regret? A Case Study in Online Learning and Games

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

AutoPR: Let's Automate Your Academic Promotion!

RealEngine: Simulating Autonomous Driving in Realistic Context

Time-Varying Optimization for Streaming Data Via Temporal Weighting

BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery

Modeling Cultural Bias in Facial Expression Recognition with Adaptive Agents

Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models

Nash equilibria for relative investors via no-arbitrage arguments