AI Agent

Advancing SLM Tool-Use Capability using Reinforcement Learning

Dhruvi Paprunia, Vansh Kharidia, Pankti Doshi

机构 * Dept. of Computer Engineering MPSTME, NMIMS（计算机工程系 MPSTME、NMIMS） 纠错

专题命中 工具调用 ：tool-use(title,abstract)；AI agent(abstract)；tool use(abstract)；function calling(abstract)

RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use

Jiajun Chai, Guojun Yin, Zekun Xu, Chuhuai Yue, Yi Jia, Siyu Xia, Xiaohan Wang, Jiwen Jiang, Xiaoguang Li, Chengqi Dong, Hang He, Wei Lin

机构 * RLFactory Team（RLFactory团队） 纠错

专题命中 工具调用 ：tool-use(title)；tool use(abstract)；workflow(abstract)；分类 cs.AI、cs.LG

Joint Resource Estimation and Trajectory Optimization for eVTOL-involved CR network: A Monte Carlo Tree Search-based Approach

Kai Xiong, Chenxin Yang, Yujie Qin, Wanzhi Ma, Chau Yuen

专题命中 工具调用 ：planning(abstract)

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

Xuan-Phi Nguyen, Shrey Pandit, Revanth Gangi Reddy, Austin Xu, Silvio Savarese, Caiming Xiong, Shafiq Joty

机构 * Salesforce AI Research（Salesforce AI研究院） 纠错

专题命中 规划决策 ：agent(abstract)；tool-use(abstract)；workflow(abstract)；agentic(abstract)

Comments Technical Report

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models

Qiming Guo, Jinwen Tang, Xingran Huang

机构 * Department of Computer Science Texas A\&M University–Corpus Christi Corpus Christi, TX, USA ； EECS Department University of Missouri Columbia, MO, USA ； Department of Computer Engineering University of California–Riverside Riverside, CA, USA 纠错

专题命中 规划决策 ：AI agent(title,abstract)；分类 cs.AI、cs.LG

Comments 6 pages, 2 figures

CAViAR: Critic-Augmented Video Agentic Reasoning

Sachit Menon, Ahmet Iscen, Arsha Nagrani, Tobias Weyand, Carl Vondrick, Cordelia Schmid

机构 * Google DeepMind（谷歌DeepMind） ； Columbia University（哥伦比亚大学） 纠错

专题命中 规划决策 ：agentic(title)；agent(abstract)；分类 cs.LG

Safe Gap-based Planning in Dynamic Settings

Max Asselmeier, Abdel Zaro, Dhruv Ahuja, Ye Zhao, Patricio A. Vela

机构 * Institute for Robotics and Intelligent Machines（机器人与智能机械研究所） ； Georgia Institute of Technology（佐治亚理工学院） ； School of Electrical and Computer Engineering（电气与计算机工程学院） 纠错

专题命中 规划决策 ：planning(title,abstract)

Comments Accepted to Algorithms for Machine Vision in Navigation and Control - Springer Publishing House

Adaptive Grasping of Moving Objects in Dense Clutter via Global-to-Local Detection and Static-to-Dynamic Planning

Hao Chen, Takuya Kiyokawa, Weiwei Wan, Kensuke Harada

机构 * Department of Systems Innovation, Graduate School of Engineering Science, Osaka University（系统创新系，工学研究科，大阪大学） 纠错

专题命中 规划决策 ：planning(title,abstract)

Comments Accepted by ICRA2025

ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Code

Kapil Madan

机构 * Principled Evolution（原则进化） 纠错

专题命中 规划决策 ：agent(abstract)；分类 cs.AI、cs.CL、cs.LG

Comments 53 pages, 7 figures, 8 tables. Open-source implementation available at: https://github.com/Principled-Evolution/argen-demo. Work explores the integration of policy-as-code for AI alignment, with a case study in culturally-nuanced, ethical AI using Dharmic principles

Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning

Pranav Pawar, Dhwaj Jain, Varun Gupta, Kaustav Dedhia, Dashrath Kale, Sudhir Dhekane

机构 * Dwarkadas J. Sanghvi College of Engineering（达沃卡斯J·桑格维工程学院） 纠错

专题命中 规划决策 ：planning(abstract)；分类 cs.AI、cs.LG

What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

机构 * Department of Computer Science Iowa State University（计算机科学系爱荷华州立大学） ； Department of Civil, Construction and Environmental Engineering Iowa State University（土木、建设与环境工程系爱荷华州立大学） 纠错

专题命中 规划决策 ：agent(abstract)；分类 cs.AI、cs.LG

CTourLLM: Enhancing LLMs with Chinese Tourism Knowledge

Qikai Wei, Mingzhi Yang, Jinqiang Wang, Wenwei Mao, Jiabo Xu, Huansheng Ning

专题命中 规划决策 ：planning(abstract)；分类 cs.AI、cs.CL

OmniAcc: Personalized Accessibility Assistant Using Generative AI

Siddhant Karki, Ethan Han, Nadim Mahmud, Suman Bhunia, John Femiani, Vaskar Raychoudhury

机构 * Miami University of Ohio（俄亥俄迈阿密大学） 纠错

专题命中 规划决策 ：planning(abstract,comments)；分类 cs.AI

Comments 11 Pages, 9 Figures, Published in the 1st Workshop on AI for Urban Planning, AAAI 2025 Workshop

XSRD-Net: EXplainable Stroke Relapse Detection

Christian Gapp, Elias Tappeiner, Martin Welk, Karl Fritscher, Stephanie Mangesius, Constantin Eisenschink, Philipp Deisl, Michael Knoflach, Astrid E. Grams, Elke R. Gizewski, Rainer Schubert

机构 * Institute of Biomedical Image Analysis UMIT TIROL -- Private University for Health Sciences（生物医学影像分析研究所） 纠错

专题命中 规划决策 ：planning(abstract)；分类 cs.AI

Comments Contribution to MICAD 2025 conference, Nov. 19-21, 2025 | London, UK

DeepGraphLog for Layered Neurosymbolic AI

Adem Kikaj, Giuseppe Marra, Floris Geerts, Robin Manhaeve, Luc De Raedt

机构 * Örebro University, Sweden（奥雷布罗大学） ； University of Antwerp, Belgium（安特卫普大学） 纠错

专题命中 规划决策 ：planning(abstract)；分类 cs.AI

A smart fridge with AI-enabled food computing

Khue Nong Thuc, Khoa Tran Nguyen Anh, Tai Nguyen Huy, Du Nguyen Hao Hong, Khanh Dinh Ba

机构 * Computer Science Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT)（计算机科学与工程学院，胡志明城大学技术学院） ； Office for International Study Programs, Ho Chi Minh City University of Technology (HCMUT)（国际研究办公室，胡志明城大学技术学院） ； Vietnam National University Ho Chi Minh City（越南国家大学胡志明市分校） ； Computer Engineering Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT)（计算机工程学院，胡志明城大学技术学院） 纠错

专题命中 规划决策 ：planning(abstract)；分类 cs.SE

Journal ref The 9th OISP Science and Technology Symposium for Students Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, 2025

Research on Conversational Recommender System Considering Consumer Types

Yaying Luo, Hui Fang, Zhu Sun

专题命中 规划决策 ：agent(abstract)；分类 cs.AI

Comments The tables Recommendation strategies for different consumer types need to be modified. Correspondence of Recommendation strategies are incorrect

Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models

Zeineb Haouari, Jonas Weidner, Yeray Martin-Ruisanchez, Ivan Ezhov, Aswathi Varma, Daniel Rueckert, Bjoern Menze, Benedikt Wiestler

机构 * Technical University of Munich（慕尼黑技术大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； University of Zurich（苏黎世大学） 纠错

专题命中 规划决策 ：planning(abstract)；分类 cs.LG

Journal ref Bildverarbeitung fuer die Medizin 2025, Informatik aktuell, Springer Vieweg, Wiesbaden (2025), pp. 57--62

A Maslow-Inspired Hierarchy of Engagement with AI Model

Madara Ogot

专题命中 规划决策 ：planning(abstract)；分类 cs.AI

Comments 30 pages, 14 tables

TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models

Zongzheng Zhang, Haobo Xu, Zhuo Yang, Chenghao Yue, Zehao Lin, Huan-ang Gao, Ziwei Wang, Hao Zhao

机构 * Beijing Academy of Artificial Intelligence, BAAI（北京人工智能研究院） ； Institute for AI Industry Research (AIR), Tsinghua Univeristy（清华大学人工智能产业研究院） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 规划决策 ：planning(abstract)

Comments Accepted to CoRL 2025, project page: \url{https://zzongzheng0918.github.io/Torque-Aware-VLA.github.io/}

Dynamic Scene 3D Reconstruction of an Uncooperative Resident Space Object

Bala Prenith Reddy Gopu, Timothy Jacob Huber, George M. Nehma, Patrick Quinn, Madhur Tiwari, Matt Ueckermann, David Hinckley, Christopher McKenna

机构 * Florida Institute of Technology（佛罗里达理工学院） ； Creare LLC（Creare公司） 纠错

专题命中 规划决策 ：planning(abstract)

Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network

Yanlong Peng, Zhigang Wang, Ziwen He, Pengxu Chang, Chuangchuang Zhou, Yu Yan, Ming Chen

机构 * School of Mechanical Engineering, Shanghai Jiao Tong University（上海交通大学机械工程学院） ； Intel Labs China（英特尔中国实验室） ； Henan Academy of Sciences（河南省科学院） ； Intel CCG FIS（英特尔中国区研究院） 纠错

专题命中 规划决策 ：planning(abstract)

Dynamic Redeployment of Nurses Across Hospitals: A Sample Robust Optimization Approach

Wei Liu, Tianchun Li, Mengshi Lu, Pengyi Shi

专题命中 规划决策 ：planning(abstract)

Performance Characterization of a Point-Cloud-Based Path Planner in Off-Road Terrain

Casey D. Majhor, Jeremy P. Bos

机构 * Robust Autonomous Systems Laboratory（鲁棒自主系统实验室） ； Department of Electrical and Computer Engineering（电气与计算机工程系） ； Michigan Technological University（密歇根技术大学） 纠错

专题命中 规划决策 ：planning(abstract)

Comments This work has been published in the Journal of Field Robotics

F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

Qi Lv, Weijie Kong, Hao Li, Jia Zeng, Zherui Qiu, Delin Qu, Haoming Song, Qizhi Chen, Xiang Deng, Jiangmiao Pang

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） 纠错

专题命中 规划决策 ：planning(abstract)

Comments Homepage: https://aopolin-lv.github.io/F1-VLA/

SAMba-UNet: SAM2-Mamba UNet for Cardiac MRI in Medical Robotic Perception

Guohao Huo, Ruiting Dai, Ling Shao, Hao Tang

机构 * University of Electronic Science and Technology of China（电子科技大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； School of Computer Science, Peking University（北京大学计算机学院） 纠错

专题命中 规划决策 ：planning(abstract)

InteractPro: A Unified Framework for Motion-Aware Image Composition

Weijing Tao, Xiaofeng Yang, Miaomiao Cui, Guosheng Lin

机构 * College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学） ； DAMO Academy, Alibaba Group（阿里达摩院） 纠错

专题命中 规划决策 ：planning(abstract)

Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control

Yan Zhang, Ahmad Mohammad Saber, Amr Youssef, Deepa Kundur

机构 * Department of Electrical and Computer Engineering, University of Toronto（电气与计算机工程系，多伦多大学） ； Concordia Institute for Information Systems Engineering（康卡迪亚信息系统工程研究所） ； Concordia University（康卡迪亚大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.AI

Efficient Multi-Agent Coordination via Dynamic Joint-State Graph Construction

Yanlin Zhou, Manshi Limbu, Xuesu Xiao

机构 * George Mason University（乔治·玛森大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Creative Agents: Simulating the Systems Model of Creativity with Generative Agents

Naomi Imasato, Kazuki Miyazawa, Takayuki Nagai, Takato Horii

机构 * Graduate School of Engineering Science, Osaka University, Osaka, Japan（大阪大学工学研究科） ； Artificial Intelligence Exploration Research Center, The University of Electro-Communications, Tokyo, Japan（电通大学人工智能探索研究中心） ； International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo, Tokyo, Japan（东京大学神经智能国际研究中心） 纠错

专题命中 多智能体 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI