AI Agent

Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning

Raphael Trumpp, Ansgar Schäfftlein, Mirco Theile, Marco Caccamo

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

Comments Reinforcement Learning Conference 2025

DRTA: Dynamic Reward Scaling for Reinforcement Learning in Time Series Anomaly Detection

Bahareh Golchin, Banafsheh Rekabdar, Kunpeng Liu

机构 * School of Computer Science Portland State University Portland, Oregon, United States（计算机科学学院波特兰州立大学波特兰俄勒冈州美国） 纠错

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

Journal ref IEEE 2025 Conference on AI, Science, Engineering, and Technology (AIxSET)

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents

Tianjian Liu, Fanqi Wan, Jiajian Guo, Xiaojun Quan

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

Comments 21 pages, 6 Figures

Survey of Specialized Large Language Model

Chenghan Yang, Ruiyu Zhao, Yang Liu, Ling Jiang

机构 * Xiaoduo AI（小多AI） ； Shanghai Jiao Tong University（上海交通大学） ； East China University of Science and Technology（东华大学） 纠错

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

Comments 9 pages, 1 figures

Statistical learning does not always entail knowledge

Daniel Andrés Díaz-Pachón, H. Renata Gallegos, Ola Hössjer, J. Sunil Rao

机构 * Division of Biostatistics, University of Miami（生物统计学系，迈阿密大学） ； Department of Mathematics, Stockholm University（数学系，斯德哥尔摩大学） ； Department of Biostatistics, University of Minnesota（生物统计学系，明尼苏达大学） 纠错

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

Comments Main file (33 pages) and supplement (16 pages). 1 figure

Playstyle and Artificial Intelligence: An Initial Blueprint Through the Lens of Video Games

Chiu-Chou Lin

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

Comments PhD Dissertation, National Yang Ming Chiao Tung University, 2025. This is the public version without Chinese abstract or postscript

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding

Daniel Bethell, Simos Gerasimou, Radu Calinescu, Calum Imrie

机构 * University of York, UK（英国约克大学） ； Cyprus University of Technology, Cyprus（塞浦路斯技术大学） 纠错

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

Comments To be published in ECAI 25

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

Yuqi Wu, Wenzhao Zheng, Sicheng Zuo, Yuanhui Huang, Jie Zhou, Jiwen Lu

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） 纠错

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

Comments Accepted by ICCV2025. Code: https://github.com/YkiWu/EmbodiedOcc

ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

Minghao Li, Ying Zeng, Zhihao Cheng, Cong Ma, Kai Jia

机构 * ByteDance BandAI（字节跳动BandAI） 纠错

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

An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage

Fan Bu, Zheng Wang, Siyi Wang, Ziyao Liu

机构 * Department of Archeology and Museology, Shanghai University（考古与博物馆学系，上海大学） ； National Collaborative Research Center for Revolutionary Cultural Heritage at Memorial of the First CPC National Congress & Shanghai University（革命文化遗产国家联合研究中心，中共一大会址纪念馆与上海大学） ； School of Management, Shanghai University（管理学院，上海大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

Testing Components of the Attention Schema Theory in Artificial Neural Networks

Kathryn T. Farrell, Kirsten Ziman, Michael S. A. Graziano

机构 * Princeton Neuroscience Institute（普林斯顿神经科学研究所） ； Department of Psychology（心理学系） 纠错

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

Pixels to Play: A Foundation Model for 3D Gameplay

Yuguang Yue, Chris Green, Samuel Hunt, Irakli Salia, Wenzhe Shi, Jonathan J Hunt

机构 * Player2 纠错

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

Journal ref Conference on Games 2025 (Short paper)

You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation

Yutong Bian, Xianhao Lin, Yupeng Xie, Tianyang Liu, Mingchen Zhuge, Siyuan Lu, Haoming Tang, Jinlin Wang, Jiayi Zhang, Jiaqi Chen, Xiangru Tang, Yongxin Ni, Sirui Hong, Chenglin Wu

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

MapStory: Prototyping Editable Map Animations with LLM Agents

Aditya Gunturu, Ben Pearman, Keiichi Ihara, Morteza Faraji, Bryan Wang, Rubaiat Habib Kazi, Ryo Suzuki

机构 * University of Calgary（卡尔加里大学） ； Adobe Research（Adobe研究） 纠错

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

Comments UIST 2025. Project page: https://adigunturu.github.io/MapStory-UIST25/

ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience

Yeana Lee Bond, Mungyeong Choe, Baker Kasim Hasan, Arsh Siddiqui, Myounghoon Jeon

机构 * Computer Science, Virginia Tech, Blacksburg, Virginia, USA（计算机科学，弗吉尼亚理工学院，弗吉尼亚州黑斯堡，美国；弗吉尼亚理工学院黑斯堡弗吉尼亚美国） ； Virginia Tech Blacksburg Virginia USA 纠错

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

Comments Submitted to International Journal of Human-Computer Studies. Bond and Choe: Drafting, Review, Editing, Validation, Software, Methodology, Investigation, Data Analysis, Conceptualization, Experiment training. Hasan and Siddiqui: Experimental and Data Analysis Support. Jeon: Supervision, Review, Resources, Project Admin, Methodology, Conceptualization. Total 34 pages

Ethics2vec: aligning automatic agents and human preferences

Gianluca Bontempi

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

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

Xiao Huang, Xu Liu, Enze Zhang, Tong Yu, Shuai Li

机构 * Shanghai Jiao Tong University, Shanghai, China（上海交通大学） ； Adobe Research, California, United States（Adobe研究院） 纠错

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

Comments ICML2025

GrandJury: A Collaborative Machine Learning Model Evaluation Protocol for Dynamic Quality Rubrics

Arthur Cho

机构 * Memoirji LLC（Memiorji公司） 纠错

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

Comments 14 pages (incl. arXiv cover), 1 table, code & dataset links inside. Open-source implementation available on PyPI (grandjury package) and GitHub. Dataset available on Hugging Face under CC-BY-4.0 license

From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning

Pusen Dong, Tianchen Zhu, Yue Qiu, Haoyi Zhou, Jianxin Li

机构 * Beihang University（北航大学） ； Zhongguancun Laboratory（中关村实验室） 纠错

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

Comments Accepted by NeurIPS 2024

AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents

Haoyu Wang, Christopher M. Poskitt, Jun Sun

机构 * Singapore Management University（新加坡管理大学） 纠错

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

Comments Accepted by the 48th IEEE/ACM International Conference on Software Engineering (ICSE 2026)

OWLViz: An Open-World Benchmark for Visual Question Answering

Thuy Nguyen, Dang Nguyen, Hoang Nguyen, Thuan Luong, Long Hoang Dang, Viet Dac Lai

机构 * Posts and Telecommunications Institute of Technology, Viet Nam（越南电信技术研究所） ； Adobe Research, USA（Adobe研究） ； University of Maryland, USA（美国马里兰大学） 纠错

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

Comments 8 pages + appendix

Evaluation and Benchmarking of LLM Agents: A Survey

Mahmoud Mohammadi, Yipeng Li, Jane Lo, Wendy Yip

机构 * SAP Labs（SAP实验室） 纠错

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

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） 纠错

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

Comments 13 pages, 6 figures

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） 纠错

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

AI-Driven Generation of Old English: A Framework for Low-Resource Languages

Rodrigo Gabriel Salazar Alva, Matías Nuñez, Cristian López, Javier Martín Arista

机构 * Universidad de Ingeniería y Tecnología (UTEC)（Ingeniería y Tecnología大学（UTEC）） ； Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET)（国家科学与技术研究理事会（CONICET）） ； Instituto de Investigaciones en Biodiversidad y Medioambiente (INIBIOMA), Universidad Nacional del Comahue（生物多样性与环境研究所（INIBIOMA），Comahue国立大学） ； Universidad de La Rioja（拉里奥ja大学） 纠错

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

Advanced System Integration: Analyzing OpenAPI Chunking for Retrieval-Augmented Generation

Robin D. Pesl, Jerin G. Mathew, Massimo Mecella, Marco Aiello

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

Comments This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in Advanced Information Systems Engineering. CAiSE 2025. Lecture Notes in Computer Science, vol 15702. Springer, Cham., and is available online at https://doi.org/10.1007/978-3-031-94571-7_8

Journal ref Advanced Information Systems Engineering. CAiSE 2025. Lecture Notes in Computer Science, vol 15702. Springer, Cham

OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?

Xuetian Chen, Yinghao Chen, Xinfeng Yuan, Zhuo Peng, Lu Chen, Yuekeng Li, Zhoujia Zhang, Yingqian Huang, Leyan Huang, Jiaqing Liang, Tianbao Xie, Zhiyong Wu, Qiushi Sun, Biqing Qi, Bowen Zhou

机构 * Fudan University（复旦大学） ； Shanghai AI Lab（上海人工智能实验室） ； Tsinghua University（清华大学） ； The University of Hong Kong（香港大学） 纠错

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

Comments Work in progress

PosterMate: Audience-driven Collaborative Persona Agents for Poster Design

Donghoon Shin, Daniel Lee, Gary Hsieh, Gromit Yeuk-Yin Chan

机构 * University of Washington（华盛顿大学） ； Adobe Inc.（Adobe公司） ； Adobe Research（Adobe研究） 纠错

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

Journal ref In Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology (UIST '25), Sept 28-Oct 1, 2025, Busan, Republic of Korea. ACM, New York, NY, USA

Assessing Adaptive World Models in Machines with Novel Games

Lance Ying, Katherine M. Collins, Prafull Sharma, Cedric Colas, Kaiya Ivy Zhao, Adrian Weller, Zenna Tavares, Phillip Isola, Samuel J. Gershman, Jacob D. Andreas, Thomas L. Griffiths, Francois Chollet, Kelsey R. Allen, Joshua B. Tenenbaum

机构 * MIT（麻省理工学院） ； Harvard University（哈佛大学） ； University of Cambridge（剑桥大学） ； Basis Research Institute（基础研究机构） ； Princeton University（普林斯顿大学） ； ARC Prize Foundation（ARC奖基金会） ； University of British Columbia（不列颠哥伦比亚大学） 纠错

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

Comments 17 pages, 4 figures

SciFi-Benchmark: Leveraging Science Fiction To Improve Robot Behavior

Pierre Sermanet, Anirudha Majumdar, Vikas Sindhwani

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

Comments Minor improvements over previous version