AI Agent

Agentic AI for Software: thoughts from Software Engineering community

Abhik Roychoudhury

机构 * NUS（国立新加坡大学） ； SonarSource SA 纠错

专题命中 软件智能体 ：agentic(title,abstract)；agent(abstract)；AI agent(abstract)；分类 cs.AI、cs.SE

Comments 4 pages

Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents

Runlong Ye, Zeling Zhang, Boushra Almazroua, Michael Liut

机构 * Computer Science, University of Toronto（计算机科学，多伦多大学） ； University of Toronto（多伦多大学） ； King Abdullah University of Science and Technology（国王 Abdullah 科学与技术大学） 纠错

专题命中 软件智能体 ：agent(abstract)；AI agent(abstract)；分类 cs.AI；planning(comments)

Comments accepted at The First Workshop on the Application of LLM Explainability to Reasoning and Planning (XLLM-Reason-Plan) @ COLM 2025

RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking

Kunrong Li, Kwan Hui Lim

机构 * Singapore University of Technology and Design（新加坡科技设计大学） 纠错

专题命中 软件智能体 ：agentic(abstract)；分类 cs.AI

Comments PRICAI 2025

Hybrid Privilege Escalation and Remote Code Execution Exploit Chains

Miguel Tulla, Andrea Vignali, Christian Colon, Giancarlo Sperli, Simon Pietro Romano, Masataro Asai, Una-May O'Reilly, Erik Hemberg

专题命中 软件智能体 ：planning(abstract)

Comments 16 pages, 12 Tables, 6 Figures, 7 Listing

VerilogMonkey: Exploring Parallel Scaling for Automated Verilog Code Generation with LLMs

Juxin Niu, Yuxin Du, Dan Niu, Xi Wang, Zhe Jiang, Nan Guan

专题命中 软件智能体 ：agentic(abstract)

UIPro: Unleashing Superior Interaction Capability For GUI Agents

Hongxin Li, Jingran Su, Jingfan Chen, Zheng Ju, Yuntao Chen, Qing Li, Zhaoxiang Zhang

机构 * University of Chinese Academy of Sciences (UCAS)（中国科学院大学） ； New Laboratory of Pattern Recognition (NLPR), CASIA（中国科学院自动化所模式识别新实验室） ； State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA（中国科学院多模态人工智能系统国家重点实验室） ； Hong Kong Institute of Science & Innovation, CASIA（中国科学院香港创新科学研究院） ； PolyU ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

专题命中 GUI与网页智能体 ：agent(abstract)；autonomous agent(abstract)；planning(abstract)

Comments Accepted to ICCV 2025

Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent

Junyu Lu, Songxin Zhang, Zejian Xie, Zhuoyang Song, Jiaxing Zhang

机构 * Lionrock AI Lab（狮岩人工智能实验室） ； China Merchants Research Institute of Advanced Technology（中国商人先进科技研究院） 纠错

专题命中 GUI与网页智能体 ：agent(title)；分类 cs.AI

Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation

Jia Li, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng

机构 * Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术创新中心） ； School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； School of Electrical Engineering and Automation, Tianjin University of Technology（天津理工大学电气工程与自动化学院） 纠错

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

Comments Main paper (14 pages). Accepted for publication by ICONIP( International Conference on Neural Information Processing) 2025

Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning

Wenda Qin, Andrea Burns, Bryan A. Plummer, Margrit Betke

机构 * Boston University（波士顿大学） 纠错

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

Comments Accepted to EMNLP 2025. Data and code to be released at https://github.com/wdqin/VLN-NAP

GPS Denied IBVS-Based Navigation and Collision Avoidance of UAV Using a Low-Cost RGB Camera

Xiaoyu Wang, Yan Rui Tan, William Leong, Sunan Huang, Rodney Teo, Cheng Xiang

机构 * Electrical and Computer Engineering Dept., National University of Singapore（新加坡国立大学电子与计算机工程系） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 GUI与网页智能体 ：planning(abstract)

AUTO-IceNav: A Local Navigation Strategy for Autonomous Surface Ships in Broken Ice Fields

Rodrigue de Schaetzen, Alexander Botros, Ninghan Zhong, Kevin Murrant, Robert Gash, Stephen L. Smith

专题命中 GUI与网页智能体 ：planning(abstract)

Comments 20 pages, 18 figures

Governed By Agents: A Survey On The Role Of Agentic AI In Future Computing Environments

Nauman Ali Murad, Safia Baloch

机构 * Faculty of Computer Science & Engineering（计算机科学与工程学院） ； GIK Institute（GIK学院） 纠错

专题命中 记忆与上下文管理 ：agentic(title,abstract)；autonomous agent(abstract)；分类 cs.AI

Federated Learning for Financial Forecasting

Manuel Noseda, Alberto De Luca, Lukas Von Briel, Nathan Lacour

机构 * ETH Zürich（苏黎世联邦理工学院） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.LG

Deep Reinforcement Learning in Factor Investment

Junlin Liu

机构 * Georgetown University（乔治城大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；分类 cs.LG

ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI

Ao Qu, Yuxi Wen, Jiayi Zhang, Yunge Wen, Yibo Zhao, Alok Prakash, Andrés F. Salazar-Gómez, Paul Pu Liang, Jinhua Zhao

专题命中 记忆与上下文管理 ：agent(abstract)

Role of Oxygen during Methane Oxidation on Pd$_1$/PdO$_1$@CeO$_2$ Surface: A Combined Density Functional Theory, Microkinetic, and Machine Learning Approach

Shalini Tomar, Hojin Jeong, Joon Hwan Choi, Seung-Cheol Lee, Satadeep Bhattacharjee

专题命中 记忆与上下文管理 ：agent(abstract)

Medical AI Consensus: A Multi-Agent Framework for Radiology Report Generation and Evaluation

Ahmed T. Elboardy, Ghada Khoriba, Essam A. Rashed

机构 * Graduate School of Information Science, University of Hyogo（京都大学垣田学园信息科学研究生院） ； Center for Informatics Science, School of Information Technology and Computer Science, Nile University（尼罗大学信息科学中心） 纠错

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

Comments NeurIPS2025 Workshop: Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis

Jeffrey Yang Fan Chiang, Seungjae Lee, Jia-Bin Huang, Furong Huang, Yizheng Chen

机构 * University of Maryland（马里兰大学） 纠错

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

Comments Project website: http://vulnerable-ai-agents.github.io

Mind the Gap: Comparing Model- vs Agentic-Level Red Teaming with Action-Graph Observability on GPT-OSS-20B

Ilham Wicaksono, Zekun Wu, Rahul Patel, Theo King, Adriano Koshiyama, Philip Treleaven

机构 * University College London（伦敦大学学院） ； Holistic AI（整体AI） 纠错

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

Comments Winner of the OpenAI GPT-OSS-20B Red Teaming Challenge (Kaggle, 2025)

Journalism-Guided Agentic In-Context Learning for News Stance Detection

Dahyun Lee, Jonghyeon Choi, Jiyoung Han, Kunwoo Park

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

Comments EMNLP 2025 (24 pages)

Controlled Yet Natural: A Hybrid BDI-LLM Conversational Agent for Child Helpline Training

Mohammed Al Owayyed, Adarsh Denga, Willem-Paul Brinkman

专题命中 Agent评测 ：agent(title,abstract)

Journal ref ACM International Conference on Intelligent Virtual Agents (IVA 2025)

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair

Jugal Gajjar, Kamalasankari Subramaniakuppusamy, Relsy Puthal, Kaustik Ranaware

机构 * Computer Science Department（计算机科学系） ； Applied Economics Department（应用经济学系） 纠错

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

Comments 6 pages, 3 figures, 4 tables, 1 algorithm, accepted in the Robustness and Security of Large Language Models (ROSE-LLM) special session at ICMLA 2025

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents

Shouju Wang, Fenglin Yu, Xirui Liu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan

机构 * Wuhan University（武汉大学） ； Microsoft（微软公司） 纠错

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

Comments To appear at EMNLP 2025 (Findings)

LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts

Junhao Chen, Jingbo Sun, Xiang Li, Haidong Xin, Yuhao Xue, Yibin Xu, Hao Zhao

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； School of Software and Microelectronics, Peking University（北京大学软件与微电子学院） ； School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院） ； Tongji University（同济大学） ； AIR, Tsinghua University（清华大学人工智能研究院） ； BAAI（百度人工智能研究院） 纠错

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

Comments Accepted by EMNLP 2025 Findings

seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs

Mohammad Ramezanali, Mo Vazifeh, Paolo Santi

机构 * Salesforce AI Palo Alto（Salesforce AI 巴尔的摩） ； Capital One ； MIT（麻省理工学院） 纠错

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

Emotions are Recognized Patterns of Cognitive Activities

Yue Jin

专题命中 Agent评测 ：agent(abstract)；autonomous agent(abstract)

Comments 10 pages, 7 figures

Applying Psychometrics to Large Language Model Simulated Populations: Recreating the HEXACO Personality Inventory Experiment with Generative Agents

Sarah Mercer, Daniel P. Martin, Phil Swatton

机构 * The Alan Turing Institute（艾伦·图灵研究所） 纠错

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

Overhearing LLM Agents: A Survey, Taxonomy, and Roadmap

Andrew Zhu, Chris Callison-Burch

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

Comments 8 pages, 1 figure

A non-smooth regularization framework for learning over multitask graphs

Yara Zgheib, Luca Calatroni, Marc Antonini, Roula Nassif

机构 * Université Côte d’Azur, I3S Laboratory, CNRS, France（法国大学皮特里特大学I3S实验室，CNRS） ； Machine Learning Genoa Center (MaLGa), Department of Computer Science, University of Genoa（热那亚大学计算机科学系机器学习中心（MaLGa）） 纠错

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

On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark

Michelangelo Conserva, Remo Sasso, Paulo Rauber

机构 * School of Electronic Engineering and Computer Science（电子工程与计算机科学学院） 纠错

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