AI Agent

A Multi-Task Evaluation of LLMs' Processing of Academic Text Input

Tianyi Li, Yu Qin, Olivia R. Liu Sheng

机构 * Department of Decisions, Operations and Technology, CUHK（决策、运营与技术系，香港中文大学） ； Department of Information Systems, Arizona State University（信息系统系，亚利桑那州立大学） 纠错

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

DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality

Qitong Chu, Yufeng Yue, Danya Yao, Huaxin Pei

机构 * School of Automation, Beijing Institute of Technology（北京理工大学自动化学院） ； Department of Automation, Tsinghua University（清华大学自动化系） 纠错

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

Not There Yet: Evaluating Vision Language Models in Simulating the Visual Perception of People with Low Vision

Rosiana Natalie, Wenqian Xu, Ruei-Che Chang, Rada Mihalcea, Anhong Guo

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

Multimodal Quantitative Measures for Multiparty Behaviour Evaluation

Ojas Shirekar, Wim Pouw, Chenxu Hao, Vrushank Phadnis, Thabo Beeler, Chirag Raman

机构 * TU Delft（代尔夫特理工大学） ； Tilburg University（蒂尔堡大学） ； Google（谷歌公司） 纠错

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

RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System

Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast

机构 * Department of Computer Science Texas A\&M University Corpus Christi, USA（计算机科学系德克萨斯A&M大学科罗拉多州科罗拉多市） 纠错

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

On Approximate MMS Allocations on Restricted Graph Classes

Václav Blažej, Michał Dębski, Zbigniew Lonc, Marta Piecyk, Paweł Rzążewski

机构 * University of Warsaw（华沙大学） ； Warsaw University of Technology（华沙技术大学） ； CISPA Helmholtz Center for Information Security（CISPA海德堡中心 for 信息 security） 纠错

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

MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming

Yuan Li, Lichao Sun, Yixuan Zhang

机构 * University of Cambridge（剑桥大学） ； Lehigh University（莱斯利大学） 纠错

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

Modeling Human Responses to Multimodal AI Content

Zhiqi Shen, Shaojing Fan, Danni Xu, Terence Sim, Mohan Kankanhalli

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

Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot

Jeroen Berrevoets, Julianna Piskorz, Robert Davis, Harry Amad, Jim Weatherall, Mihaela van der Schaar

机构 * University of Cambridge（剑桥大学） ； AstraZeneca（阿斯利康） 纠错

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

A Two-Stage Learning-to-Defer Approach for Multi-Task Learning

Yannis Montreuil, Shu Heng Yeo, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi

机构 * School of Computing, National University of Singapore, Singapore（新加坡国立大学计算机学院） ； IRIT, Université de Toulouse, CNRS, Toulouse INP, Toulouse, France（图卢兹大学IRIT研究所，法国国家科学研究中心，图卢兹INP） ； Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore（新加坡资讯与通信研究院，新加坡科技研究局） 纠错

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

Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution

Alex Clinton, Yiding Chen, Xiaojin Zhu, Kirthevasan Kandasamy

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Cornell University（康奈尔大学） 纠错

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

Comments ICML 2025

Generating Feasible and Diverse Synthetic Populations Using Diffusion Models

Min Tang, Peng Lu, Qing Feng

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

Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding

Maxim A. Patratskiy, Alexey K. Kovalev, Aleksandr I. Panov

机构 * MIPT（莫斯科物理技术学院） ； AIRI（人工智能研究院） 纠错

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

Noise-Aware Generative Microscopic Traffic Simulation

Vindula Jayawardana, Catherine Tang, Junyi Ji, Jonah Philion, Xue Bin Peng, Cathy Wu

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Vanderbilt University（范德比大学） ； NVIDIA Corporation（NVIDIA公司） 纠错

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

WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

Zimu Lu, Yunqiao Yang, Houxing Ren, Haotian Hou, Han Xiao, Ke Wang, Weikang Shi, Aojun Zhou, Mingjie Zhan, Hongsheng Li

机构 * Multimedia Laboratory (MMLab), The Chinese University of Hong Kong（香港中文大学多媒体实验室） 纠错

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

A Research Agenda for Usability and Generalisation in Reinforcement Learning

Dennis J. N. J. Soemers, Spyridon Samothrakis, Kurt Driessens, Mark H. M. Winands

机构 * Department of Advanced Computing Sciences, Maastricht University（马斯特里赫特大学高级计算科学系） ； Institute for Analytics and Data Science, University of Essex（埃塞克斯大学分析与数据科学研究所） 纠错

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

Comments To appear in Revised Selected Papers for ICAART 2025. Extended version of ICAART 2025 publication

Position: Lifetime tuning is incompatible with continual reinforcement learning

Golnaz Mesbahi, Parham Mohammad Panahi, Olya Mastikhina, Steven Tang, Martha White, Adam White

机构 * Department of Computing Science, University of Alberta, Edmonton, Canada（阿尔伯塔大学计算机科学系） ； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所） ； Canada CIFAR AI Chair（加拿大 CIFAR 人工智能主席） 纠错

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

Comments ICML 2025, position track: https://icml.cc/virtual/2025/poster/40153

Automated Visualization Makeovers with LLMs

Siddharth Gangwar, David A. Selby, Sebastian J. Vollmer

机构 * University of Kaiserslautern–Landau (RPTU)（凯撒斯劳滕-兰道大学（RPTU）） ； Department of Data Science and its Applications, German Research Center for Artificial Intelligence (DFKI)（数据科学及其应用系，德国人工智能研究中心（DFKI）） 纠错

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

Empathetic Conversational Agents: Utilizing Neural and Physiological Signals for Enhanced Empathetic Interactions

Nastaran Saffaryazdi, Tamil Selvan Gunasekaran, Kate Laveys, Elizabeth Broadbent, Mark Billinghurst

机构 * Empathic Computing Lab, Auckland Bioengineering Institute, University of Auckland（同理心计算实验室，奥克兰生物工程研究所，奥克兰大学） ； Department of Psychological Medicine, Faculty of Health Psychology, University of Auckland（心理医学系，健康心理学学院，奥克兰大学） 纠错

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

Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action

Tongyoung Kim, Jeongeun Lee, Soojin Yoon, Sunghwan Kim, Dongha Lee

机构 * Yonsei University（延世大学） 纠错

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

Challenges in Applying Variational Quantum Algorithms to Dynamic Satellite Network Routing

Phuc Hao Do, Tran Duc Le

机构 * Department of Telecommunication Engineering, Bonch-Bruevich St. Petersburg State University of Telecommunications（圣彼得堡电信大学电信工程系） ； Mathematics, Statistics and Computer Science, University of Wisconsin–Stout（威斯康星州立大学斯普林格分校数学、统计与计算机科学系） 纠错

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

Comments 17 pages and 3 figures

DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving

Longling Geng, Huangxing Li, Viktor Lado Naess, Mert Pilanci

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

Mechanism Design for Facility Location using Predictions

Toby Walsh

机构 * AI Institute, UNSW Sydney（AI研究所，新南威尔士大学悉尼分校） 纠错

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

Comments To appear in Proceedings oj IJCAI 2025 workshop on Computational Fair Division

Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs

Zuxin Ma, Yunhe Cui, Yongbin Qin

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

Strategic Hypothesis Testing

Safwan Hossain, Yatong Chen, Yiling Chen

机构 * Harvard University（哈佛大学） ； MPI for Intellgent Systems（智能系统马克思普朗克研究所） 纠错

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

Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?

Seungbin Yang, ChaeHun Park, Taehee Kim, Jaegul Choo

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

SU-ESRGAN: Semantic and Uncertainty-Aware ESRGAN for Super-Resolution of Satellite and Drone Imagery with Fine-Tuning for Cross Domain Evaluation

Prerana Ramkumar

专题命中 Agent评测 ：planning(abstract)；分类 cs.LG

How Far Are AI Scientists from Changing the World?

Qiujie Xie, Yixuan Weng, Minjun Zhu, Fuchen Shen, Shulin Huang, Zhen Lin, Jiahui Zhou, Zilan Mao, Zijie Yang, Linyi Yang, Jian Wu, Yue Zhang

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

A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values

Daniel Beechey, Thomas M. S. Smith, Özgür Şimşek

机构 * University of Bath（巴斯大学） 纠错

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

Chatting with your ERP: A Recipe

Jorge Ruiz Gómez, Lidia Andrés Susinos, Jorge Alamo Olivé, Sonia Rey Osorno, Manuel Luis Gonzalez Hernández

机构 * Instituto Tecnológico de Castilla y León（卡斯蒂利亚-莱昂技术学院） 纠错

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

Comments 11 pages, includes 3 tables summarizing schema and model performance. Submitted on July 31, 2025. Targets integration of LLM agents with ERP systems using open-weight models and Ollama deployment