AI Agent

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation

Dongyoon Hahm, Taywon Min, Woogyeol Jin, Kimin Lee

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

Comments Accepted at AAAI 2026 AI Alignment Track, Source code: https://github.com/HahmDY/agentic-ft-safety

KForge: Program Synthesis for Diverse AI Hardware Accelerators

Taras Sereda, Tom St. John, Burak Bartan, Natalie Serrino, Sachin Katti, Zain Asgar

机构 * Anonymous Authors（匿名作者） 纠错

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

Comments Under review at MLSys 2026

InData: Towards Secure Multi-Step, Tool-Based Data Analysis

Karthikeyan K, Raghuveer Thirukovalluru, Bhuwan Dhingra, David Edwin Carlson

专题命中 软件智能体 ：tool-use(abstract)；分类 cs.CL、cs.LG

Cybersecurity AI: Hacking the AI Hackers via Prompt Injection

Víctor Mayoral-Vilches, Per Mannermaa Rynning

专题命中 软件智能体 ：AI agent(abstract)

MMWOZ: Building Multimodal Agent for Task-oriented Dialogue

Pu-Hai Yang, Heyan Huang, Heng-Da Xu, Fanshu Sun, Xian-Ling Mao, Chaoxu Mu

机构 * School of Artificial Intelligence, Anhui University, Hefei, China（人工智能学院，安徽大学，合肥，中国） ； School of Computer Science（计算机科学学院） ； School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China（计算机科学与技术学院，北京理工大学，北京，中国） 纠错

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

MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements

SeokJoo Kwak, Jihoon Kim, Boyoun Kim, Jung Jae Yoon, Wooseok Jang, Jeonghoon Hong, Jaeho Yang, Yeong-Dae Kwon

机构 * Samsung SDS（三星SDS） 纠错

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

Comments 26 pages, 7 figures. Code available at https://github.com/samsungsds-research-papers/mega-gui

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

Guangyi Liu, Pengxiang Zhao, Yaozhen Liang, Liang Liu, Yaxuan Guo, Han Xiao, Weifeng Lin, Yuxiang Chai, Yue Han, Shuai Ren, Hao Wang, Xiaoyu Liang, WenHao Wang, Tianze Wu, Zhengxi Lu, Siheng Chen, LiLinghao, Hao Wang, Guanjing Xiong, Yong Liu, Hongsheng Li

专题命中 GUI与网页智能体 ：agent(abstract)；multi-agent(abstract)

Comments Paper accepted to TMLR 2025, Project Homepage: https://github.com/PhoneLLM/Awesome-LLM-Powered-Phone-GUI-Agents

Autonomous Underwater Cognitive System for Adaptive Navigation: A SLAM-Integrated Cognitive Architecture

K. A. I. N Jayarathne, R. M. N. M. Rathnayaka, D. P. S. S. Peiris

机构 * Department of Computational Mathematics University of Moratuwa（计算数学系大学莫图瓦） 纠错

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

Comments 6 pages, 2 figures

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents

Fuyao Zhang, Jiaming Zhang, Che Wang, Xiongtao Sun, Yurong Hao, Guowei Guan, Wenjie Li, Longtao Huang, Wei Yang Bryan Lim

专题命中 GUI与网页智能体 ：agent(abstract)

RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation

Xiaoshuai Hao, Yingbo Tang, Lingfeng Zhang, Yanbiao Ma, Yunfeng Diao, Ziyu Jia, Wenbo Ding, Hangjun Ye, Long Chen

机构 * Xiaomi EV（小米电动车） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学 Gallagher人工智能学院） ； School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院） 纠错

专题命中 GUI与网页智能体 ：planning(abstract)

MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning

Ye Bai, Minghan Wang, Thuy-Trang Vu

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，墨尔本大学） 纠错

专题命中 记忆与上下文管理 ：agent(title,abstract)；planning(title,abstract)；multi-agent(title,abstract)；分类 cs.CL

Comments 27 pages, 11 figures, ALTA 2025

Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

Haorui He, Yupeng Li, Bin Benjamin Zhu, Dacheng Wen, Reynold Cheng, Francis C. M. Lau

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

Comments Accepted by AAAI 2026 (Oral). Code available at: https://trustworthycomp.github.io/Fact2Fiction/

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

Shalini Maiti, Amar Budhiraja, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach

机构 * Meta SuperIntelligence Labs（Meta超智能实验室） ； FAIR at Meta（Meta的FAIR部门） ； University College London（伦敦大学学院） 纠错

专题命中 记忆与上下文管理 ：function calling(abstract)；分类 cs.CL

GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory

Jeong Hun Yeo, Sangyun Chung, Sungjune Park, Dae Hoe Kim, Jinyoung Moon, Yong Man Ro

机构 * Integrated Vision and Language Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST)（整合视觉与语言实验室，电气工程学院，韩国科学技术院（KAIST）） ； Visual Intelligence Research Section, Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute (ETRI)（视觉智能研究部，超智能创意研究实验室，电子电信研究院） 纠错

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

TM-UNet: Token-Memory Enhanced Sequential Modeling for Efficient Medical Image Segmentation

Yaxuan Jiao, Qing Xu, Yuxiang Luo, Xiangjian He, Zhen Chen, Wenting Duan

机构 * Dalian University of Technology（大连理工大学） ； University of Lincoln（林肯大学） ； University of Nottingham（诺丁汉大学） ； Waseda University（早稻田大学） ； University of Nottingham Ningbo China（宁波诺丁汉大学） ； Yale University（耶鲁大学） 纠错

专题命中 记忆与上下文管理 ：planning(abstract)

Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)

Rodolfo Valiente, Praveen K. Pilly

机构 * Intelligent Systems Center, HRL Laboratories（智能系统中心，HRL实验室） 纠错

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

Comments Replaced all references to "self-awareness" with the more accurate term "self-assessment"; Updated Figure 2; Added recent pertinent work from the cognitive computational neuroscience literature; Removed the non-apples-to-apples comparison with Dreamer-v3 for self-assessment; Added additional experiments to validate the role of accurate self-assessment in effective self-regulation

MARC: Multimodal and Multi-Task Agentic Retrieval-Augmented Generation for Cold-Start Recommender System

Seung Hwan Cho, Yujin Yang, Danik Baeck, Minjoo Kim, Young-Min Kim, Heejung Lee, Sangjin Park

机构 * Department of Industrial Data Engineering, Hanyang University, Republic of Korea（工业数据工程系，翰阳大学） ； School of Interdisciplinary Industrial Studies, Hanyang University, Republic of Korea（跨学科工业研究学院，翰阳大学） 纠错

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

Comments 13 pages, 2 figures, Accepted at RDGENAI at CIKM 2025 workshop

FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights

Chengzhang Yu, Yiming Zhang, Zhixin Liu, Zenghui Ding, Yining Sun, Zhanpeng Jin

机构 * South China University of Technology（南方科技大学） ； HFIPS, Chinese Academy of Sciences（中国科学院HFIPS） ； University of Science and Technology of China（中国科学技术大学） ； The Third Affiliated Hospital of SuYat-sen University（孙逸德大学第三附属医院） 纠错

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

Comments 12 pages, 4 figures, 5 table

Mixture-of-Schedulers: An Adaptive Scheduling Agent as a Learned Router for Expert Policies

Xinbo Wang, Shian Jia, Ziyang Huang, Jing Cao, Mingli Song

机构 * Zhejiang University（浙江大学） ； HangZhou City University（杭州市大学） 纠错

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

Personalizing Prostate Cancer Education for Patients Using an EHR-Integrated LLM Agent

Yuexing Hao, Jason Holmes, Mark R. Waddle, Brian J. Davis, Nathan Y. Yu, Kristin Vickers, Heather Preston, Drew Margolin, Corinna E. Lockenhoff, Aditya Vashistha, Saleh Kalantari, Marzyeh Ghassemi, Wei Liu

专题命中 Agent评测 ：agent(title,abstract)

Journal ref npj Digital Medicine 2025

Agent-Based Modelling in Cellular Biology - Are we flexible yet?

Jonas Pleyer

专题命中 Agent评测 ：agent(title,abstract)

VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

Hao Wang, Eiki Murata, Lingfang Zhang, Ayako Sato, So Fukuda, Ziqi Yin, Wentao Hu, Keisuke Nakao, Yusuke Nakamura, Sebastian Zwirner, Yi-Chia Chen, Hiroyuki Otomo, Hiroki Ouchi, Daisuke Kawahara

机构 * Waseda University（早稻田大学） ； CyberAgent, Inc.（CyberAgent公司） ； AI Shift, Inc.（AI Shift公司） ； Nara Institute of Science and Technology（奈良研究所） 纠错

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

Comments AAAI 2026

DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents

Qi Li, Jianjun Xu, Pingtao Wei, Jiu Li, Peiqiang Zhao, Jiwei Shi, Xuan Zhang, Yanhui Yang, Xiaodong Hui, Peng Xu, Wenqin Shao

机构 * Beijing Caizhi Tech（北京彩智科技） 纠错

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

DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs

WenZhuo Zhu, Zheng Cui, Wenhan Lu, Sheng Liu, Yue Zhao

机构 * Zhejiang University（浙江大学） ； University of Toronto（多伦多大学） ； Peking University（北京大学） 纠错

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

DiffFP: Learning Behaviors from Scratch via Diffusion-based Fictitious Play

Akash Karthikeyan, Yash Vardhan Pant

机构 * Department of Electrical and Computer Engineering, University of Waterloo（滑铁卢大学电气与计算机工程系） 纠错

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

Comments Initial results presented at the IJCAI 2025 Workshop on User-Aligned Assessment of Adaptive AI Systems. Project page: https://aku02.github.io/projects/difffp/

AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

Qingyu Zhang, Chunlei Xin, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Qing Ye, Qianlong Xie, Xingxing Wang

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

LLM-driven Provenance Forensics for Threat Investigation and Detection

Kunal Mukherjee, Murat Kantarcioglu

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

Graph Neural Network-Based Reinforcement Learning for Controlling Biological Networks - the GATTACA Framework

Andrzej Mizera, Jakub Zarzycki

机构 * Faculty of Mathematics, Informatics and Mechanics, University of Warsaw（数学、信息学与力学学院，华沙大学） ； IDEAS Research Institute（IDEAS研究机构） ； IDEAS NCBR Sp. z o.o.（IDEAS NCBR公司） 纠错

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

Using Linearized Optimal Transport to Predict the Evolution of Stochastic Particle Systems

Nicholas Karris, Evangelos A. Nikitopoulos, Ioannis G. Kevrekidis, Seungjoon Lee, Alexander Cloninger

机构 * University of Michigan（密歇根大学） ； Johns Hopkins University（约翰霍普金斯大学） ； California State University, Long Beach（长滩加州州立大学） 纠错

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

Historical/temporal necessities/possibilities, and a logical theory of them in branching time

Fengkui Ju, Woxuan Zhou

机构 * School of Philosophy, Beijing Normal University（北京师范大学哲学学院） ； Institute for Logic, Language and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所） 纠错

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