AI Agent

2510.14611 2025-10-17 cs.HC cs.AI 57%

An Active Inference Model of Mouse Point-and-Click Behaviour

Markus Klar, Sebastian Stein, Fraser Paterson, John H. Williamson, Roderick Murray-Smith

机构 * University of Glasgow（格拉斯哥大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 12 pages + Appendix; Accepted to 6th International Workshop on Active Inference (IWAI 2025)

2510.13925 2025-10-17 cs.CL cs.CR cs.NI 88%

An LLM-Powered AI Agent Framework for Holistic IoT Traffic Interpretation

Daniel Adu Worae, Spyridon Mastorakis

机构 * University of Notre Dame（内布拉斯加大学达灵顿分校）

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

2510.14969 2025-10-17 cs.CL cs.AI cs.LG 82%

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

Yiming Wang, Da Yin, Yuedong Cui, Ruichen Zheng, Zhiqian Li, Zongyu Lin, Di Wu, Xueqing Wu, Chenchen Ye, Yu Zhou, Kai-Wei Chang

机构 * UCLA（加州大学洛杉矶分校）； Harvard University（哈佛大学）

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

Comments Preprint. Project page: https://ui-simulator.notion.site/llms-as-scalable-digital-world-simulator; Code and data: https://github.com/WadeYin9712/UI-Simulator

2503.12349 2025-10-17 cs.AI 81%

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

Jianzhu Yao, Kevin Wang, Ryan Hsieh, Haisu Zhou, Tianqing Zou, Zerui Cheng, Zhangyang Wang, Pramod Viswanath

机构 * Princeton University（普林斯顿大学）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）； Sentient Foundation（Sentient基金会）

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

Comments 48 pages, 7 figures

2510.13857 2025-10-17 cs.SE cs.AI 81%

From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering

Qiang Xu, Xiangyu Wen, Changran Xu, Zeju Li, Jianyuan Zhong

机构 * CURE Lab., Dept. of CSE, The Chinese University of Hong Kong, Hong Kong S.A.R.（CUHK计算机科学与工程系CURE实验室）

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

2508.16508 2025-10-17 cs.MA cs.SE 79%

ABMax: A JAX-based Agent-based Modeling Framework

Siddharth Chaturvedi, Ahmed El-Gazzar, Marcel van Gerven

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

Comments 8 pages, 7 figures, 4 tables, 2 algorithms

2510.13835 2025-10-17 cs.CL cs.AI 79%

ConDABench: Interactive Evaluation of Language Models for Data Analysis

Avik Dutta, Priyanshu Gupta, Hosein Hasanbeig, Rahul Pratap Singh, Harshit Nigam, Sumit Gulwani, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari

机构 * Microsoft（微软）

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

2510.14902 2025-10-17 cs.RO 78%

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

Han Zhao, Jiaxuan Zhang, Wenxuan Song, Pengxiang Ding, Donglin Wang

专题命中 Agent评测：agentic(title,abstract)

2510.14677 2025-10-17 cs.RO cs.AI cs.LG cs.MA 73%

When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks

Steffen Hagedorn, Luka Donkov, Aron Distelzweig, Alexandru P. Condurache

机构 * Robert Bosch GmbH（罗伯特·博世有限公司）； Institute for Neuro- and Bioinformatics, University of Lübeck（神经与生物医学研究所，吕贝克大学）； Engineering Faculty, DHBW Stuttgart（工程学院，斯图加特DHBW）； Department of Computer Science, University of Freiburg（计算机科学系，弗赖堡大学）

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

2503.20934 2025-10-17 cs.SE cs.AI 62%

Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring

Abhiram Bellur, Fraol Batole, Mohammed Raihan Ullah, Malinda Dilhara, Yaroslav Zharov, Timofey Bryksin, Kai Ishikawa, Haifeng Chen, Masaharu Morimoto, Shota Motoura, Takeo Hosomi, Tien N. Nguyen, Hridesh Rajan, Nikolaos Tsantalis, Danny Dig

机构 * University of Colorado（科罗拉多大学）； Tulane University（路易斯安那州立大学）； Amazon Web Services（亚马逊网络服务）； JetBrains Research（JetBrains研究）； NEC Corporation（日本电报电话公司）； NEC Laboratories America（日本电报电话美洲实验室）； University of Texas at Dallas（德克萨斯大学达拉斯分校）； Concordia University（康科迪亚大学）； University of Colorado, JetBrains Research（科罗拉多大学，JetBrains研究）

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

Comments Published at the International Conference on Software Maintenance and Evolution (ICSME'25)

2502.04426 2025-10-17 cs.CL cs.AI cs.CY 62%

The simulation of judgment in LLMs

Edoardo Loru, Jacopo Nudo, Niccolò Di Marco, Alessandro Santirocchi, Roberto Atzeni, Matteo Cinelli, Vincenzo Cestari, Clelia Rossi-Arnaud, Walter Quattrociocchi

机构 * Department of Computer, Control and Management Engineering, Sapienza University of Rome（计算机、控制与管理工程系，罗马萨皮恩扎大学）； Department of Computer Science, Sapienza University of Rome（计算机科学系，罗马萨皮恩扎大学）； Department of Legal, Social, and Educational Sciences, Tuscia University（法律、社会与教育科学系，图斯西亚大学）； Department of Psychology, Sapienza University of Rome（心理学系，罗马萨皮恩扎大学）

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

Comments Please refer to published version: https://doi.org/10.1073/pnas.2518443122

Journal ref Proc. Natl. Acad. Sci. U.S.A. 122 (42) e2518443122, 2025

2510.14966 2025-10-17 cs.LG stat.ML 57%

Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores

Zachary Robertson

机构 * Stanford University（斯坦福大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 9 pages, 2 figures

2510.14700 2025-10-17 cs.SE cs.CR 57%

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?

Bin Liu, Yanjie Zhao, Guoai Xu, Haoyu Wang

专题命中 Agent评测：agent(abstract)；分类 cs.SE

2510.14653 2025-10-17 cs.SE cs.RO 57%

Requirement Identification for Traffic Simulations in Driving Simulators

Sven Tarlowski, Lutz Eckstein

专题命中 Agent评测：agent(abstract)；分类 cs.SE

Comments 2 Pages, 1 figure

2510.14503 2025-10-17 cs.LG 57%

Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals

Andrejs Sorstkins, Omer Tariq, Muhammad Bilal

机构 * School of Computing and Communications, Lancaster University, Lancaster LA1 4WA, United Kingdom（1 计算与通信学院，兰卡斯特大学，英国兰卡斯特 LA1 4WA）； Neubility, 2F 115 (04768) Wangsimni-ro, Seongdong-gu, Seoul, South Korea（2 Neubility，韩国首尔松江区 Wangsimni-ro 2F 115 (04768)）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Submitted PLOS ONE

2501.13481 2025-10-17 cs.GT cs.AI cs.DM 57%

Polynomial-Time Algorithms for Fair Orientations of Chores

Kevin Hsu, Valerie King

机构 * University of Victoria（维多利亚大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 8 pages, to appear in ECAI 2025

2405.09831 2025-10-17 stat.ML cs.LG 57%

Nearly Minimax Optimal Regret for Multinomial Logistic Bandit

Joongkyu Lee, Min-hwan Oh

机构 * Seoul National University（首尔国立大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted at NeurIPS 2024

2510.14965 2025-10-17 cs.CV 50%

ChangingGrounding: 3D Visual Grounding in Changing Scenes

Miao Hu, Zhiwei Huang, Tai Wang, Jiangmiao Pang, Dahua Lin, Nanning Zheng, Runsen Xu

机构 * Xi’an Jiaotong University（西安交通大学）； Zhejiang University（浙江大学）； The Chinese University of Hong Kong（香港中文大学）； Shanghai AI Laboratory（上海人工智能实验室）

专题命中 Agent评测：agent(abstract)

Comments 30 pages

2501.12498 2025-10-17 cs.CY cs.HC 50%

The Start Button Problem: a basis for human responsibility in artificial intelligence computation

Vincenzo Calderonio

专题命中 Agent评测：agent(abstract)

Comments 14 pages

2510.14278 2025-10-17 cs.CL cs.AI cs.IR 81%

PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering

Md Mahadi Hasan Nahid, Davood Rafiei

机构 * Department of Computing Science University of Alberta（计算科学系阿尔伯塔大学）

专题命中其他Agent ：agentic(title,abstract)；分类 cs.AI、cs.CL

Comments 18 pages

2510.10520 2025-10-17 cs.CY cs.RO 50%

AI-Agents for Culturally Diverse Online Higher Education Environments

Fuze Sun, Paul Craig, Lingyu Li, Shixiangyue Meng, Chuxi Nan

专题命中其他Agent ：AI agent(abstract)

1. 记忆与上下文管理 3 篇

An Active Inference Model of Mouse Point-and-Click Behaviour

2. Agent评测 18 篇

An LLM-Powered AI Agent Framework for Holistic IoT Traffic Interpretation

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering

ABMax: A JAX-based Agent-based Modeling Framework

ConDABench: Interactive Evaluation of Language Models for Data Analysis

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks

Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring

The simulation of judgment in LLMs

Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?

Requirement Identification for Traffic Simulations in Driving Simulators

Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals

Polynomial-Time Algorithms for Fair Orientations of Chores

Nearly Minimax Optimal Regret for Multinomial Logistic Bandit

ChangingGrounding: 3D Visual Grounding in Changing Scenes

The Start Button Problem: a basis for human responsibility in artificial intelligence computation

3. 其他Agent 2 篇

PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering

AI-Agents for Culturally Diverse Online Higher Education Environments