AI Agent

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang, Xinhao Yi, Guibin Zhang, Yi Xu, Bin Wu, Siwei Liu, Zihao Li, Zhaochun Ren, Nikos Aletras, Xi Wang, Han Zhou, Zaiqiao Meng

机构 * University of Glasgow（格拉斯哥大学） ； University of Sheffield（谢菲尔德大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； National University of Singapore（新加坡国家大学） ； University of Cambridge（剑桥大学） ； University College London（伦敦大学学院） ； University of Aberdeen（阿伯丁大学） ； Leiden University（莱顿大学） 纠错

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

Comments Github Repo: https://github.com/EvoAgentX/Awesome-Self-Evolving-Agents

Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025

Jiahao Qiu, Jingzhe Shi, Xinzhe Juan, Zelin Zhao, Jiayi Geng, Shilong Liu, Hongru Wang, Sanfeng Wu, Mengdi Wang

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

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents

Tianmi Ma, Jiawei Du, Wenxin Huang, Wenjie Wang, Liang Xie, Xian Zhong, Joey Tianyi Zhou

机构 * Wuhan University of Technology（武汉理工大学） ； Agency for Science, Technology and Research, Singapore（新加坡科技研究局） ； Hubei University（湖北大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

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

Oversight Structures for Agentic AI in Public-Sector Organizations

Chris Schmitz, Jonathan Rystrøm, Jan Batzner

机构 * Centre for Digital Governance, Hertie School（数字治理中心，赫尔姆斯学校） ； Oxford Internet Institute, University of Oxford（牛津互联网研究所，牛津大学） ； Weizenbaum Institute Berlin, Germany（贝伦贝格Weizenbaum研究所） ； Technical University Munich, Germany（慕尼黑技术大学） 纠错

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

Comments To appear at REALM@ACL2025

Journal ref Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025), pages 298-308, Vienna, Austria. Association for Computational Linguistics

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

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

GridMind: LLMs-Powered Agents for Power System Analysis and Operations

Hongwei Jin, Kibaek Kim, Jonghwan Kwon

机构 * Argonne National Laboratory（阿贡国家实验室） 纠错

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

Comments 11 pages, 9 figures, 2 tables. Work under review

Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation

Teddy Lazebnik, Labib Shami

专题命中 Agent评测 ：agent(title,abstract)

Self-respecting worker in the precarious gig economy: A dynamic principal-agent model

Zsolt Bihary, Péter Csóka, Péter Kerényi, Alexander Szimayer

专题命中 Agent评测 ：agent(title,abstract)

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

Xuhui Zhou, Hyunwoo Kim, Faeze Brahman, Liwei Jiang, Hao Zhu, Ximing Lu, Frank Xu, Bill Yuchen Lin, Yejin Choi, Niloofar Mireshghallah, Ronan Le Bras, Maarten Sap

机构 * Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所） ； Allen Institute for AI（人工智能研究院） 纠错

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

Comments Both the second and third authors contributed equally

Multiple LLM Agents Debate for Equitable Cultural Alignment

Dayeon Ki, Rachel Rudinger, Tianyi Zhou, Marine Carpuat

机构 * University of Maryland（马里兰大学） 纠错

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

Comments ACL 2025 (Oral)

The Impact of Sequential versus Parallel Clearing Mechanisms in Agent-Based Simulations of Artificial Limit Order Book Exchanges

Matej Steinbacher, Mitja Steinbacher, Matjaz Steinbacher

专题命中 Agent评测 ：agent(title)

Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation

Adib Bazgir, Amir Habibdoust, Yuwen Zhang, Xing Song

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

Comments 24 pages. 2 figures

Universal Deep Research: Bring Your Own Model and Strategy

Peter Belcak, Pavlo Molchanov

机构 * NVIDIA Research（NVIDIA研究） 纠错

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

AI Chaperones Are (Really) All You Need to Prevent Parasocial Relationships with Chatbots

Emma Rath, Stuart Armstrong, Rebecca Gorman

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

Conformal Predictive Monitoring for Multi-Modal Scenarios

Francesca Cairoli, Luca Bortolussi, Jyotirmoy V. Deshmukh, Lars Lindemann, Nicola Paoletti

机构 * University of Trieste, Trieste, Italy（特里埃斯特大学） ； University of Southern California, Los Angeles, California（南加州大学） ； King's College London, London, United Kingdom（伦敦国王学院） 纠错

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

Analysing contrarian behaviour using nonlinear biased $q$-voter model

Amit Pradhan, Pratik Mullick, Parongama Sen

专题命中 Agent评测 ：agent(abstract)

Comments 15 pages, 9 figures

Counterfactual Local Friendliness: An epsilon-Bounded Interaction-Free Paradox and a Disturbance-Robust Three-Box Inequality

Maximilian Ralph Peter von Liechtenstein

专题命中 Agent评测 ：agent(abstract)

Comments 10 pages, 2 figures. Theoretical results only

Jet-Feedback on kpc scales: a review

Dipanjan Mukherjee

专题命中 Agent评测 ：agent(abstract)

Comments Accepted for publication in Galaxies, MPDI

Combinatorial Contracts

Paul Duetting, Tomer Ezra, Michal Feldman, Thomas Kesselheim

专题命中 Agent评测 ：agent(abstract)

Comments Accepted for publication in SIAM Journal on Computing (SICOMP). A preliminary version appeared in FOCS 2021

Safe and Efficient Lane-Changing for Autonomous Vehicles: An Improved Double Quintic Polynomial Approach with Time-to-Collision Evaluation

Rui Bai, Rui Xu, Teng Rui, Jiale Liu, Qi Wei Oung, Hoi Leong Lee, Zhen Tian, Fujiang Yuan

专题命中 Agent评测 ：planning(abstract)

Delayed Interactions in Active Agents: Stability and Formations

Yu Wang, Andreas Amann, Jinde Cao, Jürgen Kurths, Serhiy Yanchuk

专题命中 Agent评测 ：agent(abstract)

Risk sharing with Lambda value at risk under heterogeneous beliefs

Peng Liu, Andreas Tsanakas, Yunran Wei

专题命中 Agent评测 ：agent(abstract)

Comments 44 pages; accepted by Finance and Stochastics

Transforming Norm-based To Graph-based Spatial Representation for Spatio-Temporal Epidemiological Models

Teddy Lazebnik

专题命中 Agent评测 ：agent(abstract)