AI Agent

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

Jonathan Light, Min Cai, Weiqin Chen, Guanzhi Wang, Xiusi Chen, Wei Cheng, Yisong Yue, Ziniu Hu

机构 * Rensselaer Polytechnic Institute（拉特加大学） ； Shenzhen University（深圳大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； NEC laboratories America（NEC美国实验室） ； California Institute of Technology（加州理工学院） 纠错

专题命中 工具调用 ：agent(abstract)；planning(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL

Comments website: https://llm-strategist.github.io

Unrolling Dynamic Programming via Graph Filters

Sergio Rozada, Samuel Rey, Gonzalo Mateos, Antonio G. Marques

机构 * Dep. of Signal Theory, King Juan Carlos University（信号理论系，国王胡安·卡洛斯大学） ； Dep. of ECE, University of Rochester（电子工程系，罗切斯特大学） 纠错

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI

Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems

Bin Liu

机构 * Home Robotics Lab, E-surfing Digital Life Technology Co., Ltd., China Telecom（居家机器人实验室，艾苏弗灵数字生命技术有限公司，中国电信） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI

Comments 16 pages

OPAL: Encoding Causal Understanding of Physical Systems for Robot Learning

Daniel Tcheurekdjian, Joshua Klasmeier, Tom Cooney, Christopher McCann, Tyler Fenstermaker

专题命中 工具调用 ：agent(abstract)；分类 cs.AI

Comments We withdraw our submission following peer review feedback that identified methodological limitations: specifically, our experimental design does not adequately support the causal claims made in the submission. The work was preliminary undergraduate research that requires substantial additional experimental validation to properly establish the proposed causal relationships

Multi-UAV Deployment in Obstacle-Cluttered Environments with LOS Connectivity

Yuda Chen, Shuaikang Wang, Jie Li, Meng Guo

机构 * Department of Mechanics and Engineering Science, College of Engineering, Peking University（力学与工程科学系，工程学院，北京大学） ； National University of Defense Technology（国防科技大学） 纠错

专题命中 工具调用 ：agent(abstract)

Comments iros2025

V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video

Jianqi Chen, Biao Zhang, Xiangjun Tang, Peter Wonka

专题命中 工具调用 ：workflow(abstract)

Comments Accepted by ICCV 2025. Project page: https://windvchen.github.io/V2M4/

Optimal Follow-Up of Gravitational-Wave Events with the UltraViolet EXplorer (UVEX)

Leo P. Singer, Alexander W. Criswell, Sydney C. Leggio, R. Weizmann Kiendrebeogo, Michael W. Coughlin, Hannah P. Earnshaw, Suvi Gezari, Brian W. Grefenstette, Fiona A. Harrison, Mansi M. Kasliwal, Brett M. Morris, Erik Tollerud, S. Bradley Cenko

专题命中 工具调用 ：planning(abstract)

Comments For data release, see https://zenodo.org/records/15176276

Journal ref PASP 137 074501 (2025)

Agentic Web: Weaving the Next Web with AI Agents

Yingxuan Yang, Mulei Ma, Yuxuan Huang, Huacan Chai, Chenyu Gong, Haoran Geng, Yuanjian Zhou, Ying Wen, Meng Fang, Muhao Chen, Shangding Gu, Ming Jin, Costas Spanos, Yang Yang, Pieter Abbeel, Dawn Song, Weinan Zhang, Jun Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； The Hong Kong University of Science and Technology（香港科技大学） ； University of Liverpool（利物浦大学） ； University of California Berkeley（加州大学伯克利分校） ； Shanghai Innovation Institute（上海创新研究院） ； University of California Davis（加州大学戴维斯分校） ； Virginia Tech（弗吉尼亚理工大学） ； University College London（伦敦大学学院） 纠错

专题命中 规划决策 ：AI agent(title,abstract)；agentic(title,abstract)；agent(abstract)；autonomous agent(abstract)

Hierarchical Game-Based Multi-Agent Decision-Making for Autonomous Vehicles

Mushuang Liu, Yan Wan, Frank Lewis, Subramanya Nageshrao, H. Eric Tseng, Dimitar Filev

专题命中 规划决策 ：agent(title,abstract)；multi-agent(title,abstract)

Comments 12 pages, 20 figures, 1 algorithm

MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation

Yi Kong, Dianxi Shi, Guoli Yang, Zhang ke-di, Chenlin Huang, Xiaopeng Li, Songchang Jin

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

StaffPro: an LLM Agent for Joint Staffing and Profiling

Alessio Maritan

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

Online Concurrent Multi-Robot Coverage Path Planning

Ratijit Mitra, Indranil Saha

机构 * Department of Computer Science and Engineering, Indian Institute of Technology Kanpur（计算机科学与工程系，印度理工学院坎浦尔） 纠错

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

Comments Accepted in IROS 2025

MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning

Tianhong Gao, Yannian Fu, Weiqun Wu, Haixiao Yue, Shanshan Liu, Gang Zhang

机构 * Baidu Inc.（百度公司） 纠错

专题命中 规划决策 ：agent(title,abstract)

Scanning Bot: Efficient Scan Planning using Panoramic Cameras

Euijeong Lee, Kyung Min Han, Young J. Kim

专题命中 规划决策 ：planning(title,abstract)

A finite time analysis of distributed Q-learning

Han-Dong Lim, Donghwan Lee

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

Comments Published at RLC2025

Planning Persuasive Trajectories Based on a Leader-Follower Game Model

Chaozhe R. He, Yichen Dong, Nan Li

专题命中 规划决策 ：planning(title)

Comments To appear at MECC 2025 (https://mecc2025.a2c2.org/)

DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation

Haoran Li, Yuli Tian, Kun Lan, Yong Liao, Lin Wang, Pan Hui, Peng Yuan Zhou

机构 * University of Science and Technology of China（中国科学技术大学） ； Nanyang Technological University（南洋理工大学） ； Hong Kong University of Science and Technology（香港科学理工大学） ； University of Helsinki（赫尔辛基大学） ； Aarhus University（奥胡斯大学） 纠错

专题命中 规划决策 ：agent(abstract)；planning(abstract)

Comments Extended version of ECCV 2024 paper "DreamScene"

The pitfalls of next-token prediction

Gregor Bachmann, Vaishnavh Nagarajan

机构 * ETH Zürich, Switzerland（苏黎世联邦理工学院） ； Google Research, US（谷歌研究院） 纠错

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

Comments ICML 2024

Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform

Justin Curry, Brennan Lagasse, Ngoc B. Lam, Gregory Cox, David Rosenbluth, Alberto Speranzon

机构 * University at Albany, SUNY（阿尔巴尼大学，SUNY） ； Lockheed Martin Corporation（洛克希德·马丁公司） 纠错

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

Comments 17 pages and 8 figures. Preliminary report. Feedback welcome!

Advancing Compositional LLM Reasoning with Structured Task Relations in Interactive Multimodal Communications

Xinye Cao, Hongcan Guo, Guoshun Nan, Jiaoyang Cui, Haoting Qian, Yihan Lin, Yilin Peng, Diyang Zhang, Yanzhao Hou, Huici Wu, Xiaofeng Tao, Tony Q. S. Quek

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

Comments Accepted by IEEE JSAC. This work has been submitted to the IEEE for possible publication

Machine Learning Risk Intelligence for Green Hydrogen Investment: Insights for Duqm R3 Auction

Obumneme Nwafor, Mohammed Abdul Majeed Al Hooti

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

Comments Updated version

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning

Yifan Wei, Xiaoyan Yu, Yixuan Weng, Tengfei Pan, Angsheng Li, Li Du

专题命中 规划决策 ：tool-use(abstract)；分类 cs.CL

Large Language Models for Supply Chain Decisions

David Simchi-Levi, Konstantina Mellou, Ishai Menache, Jeevan Pathuri

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

Comments Forthcoming chapter in AI in Supply Chains: Perspectives from Global Thought Leaders, edited by Maxime C. Cohen and Tinglong Dai, and part of the Springer Series in Supply Chain Management (edited by Prof. Chris Tang)

Can LLMs Reason About Trust?: A Pilot Study

Anushka Debnath, Stephen Cranefield, Emiliano Lorini, Bastin Tony Roy Savarimuthu

机构 * National Institute of Technology, Durgapur, India（印度达格apur国立理工学院） ； University of Otago, New Zealand（新西兰奥塔哥大学） ； IRIT, CNRS, Toulouse University, France（法国图卢兹大学IRIT与CNRS） 纠错

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

Comments 17 pages, 5 figures, 3 tables Accepted for presentation as a full paper at the COINE 2025 workshop at AAMAS 2025 see https://coin-workshop.github.io/coine-2025-detroit/accepted_for_presentation.html

Empowering Educators in the Age of AI: An Empirical Study on Creating custom GPTs in Qualitative Research Method education

Qian Huang, Thijs Willems

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

Comments 20 pages

Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots

Wei Cui, Haoyu Wang, Wenkang Qin, Yijie Guo, Gang Han, Wen Zhao, Jiahang Cao, Zhang Zhang, Jiaru Zhong, Jingkai Sun, Pihai Sun, Shuai Shi, Botuo Jiang, Jiahao Ma, Jiaxu Wang, Hao Cheng, Zhichao Liu, Yang Wang, Zheng Zhu, Guan Huang, Jian Tang, Qiang Zhang

机构 * X-Humanoid ； GigaAI Project（GigaAI项目） 纠错

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

Comments Tech Report

VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback

Jianxin Bi, Kevin Yuchen Ma, Ce Hao, Mike Zheng Shou, Harold Soh

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

Comments 19 pages, 5 figures

Prediction accuracy versus rescheduling flexibility in elective surgery management

Pieter Smet, Martina Doneda, Ettore Lanzarone, Giuliana Carello

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

FedStrategist: A Meta-Learning Framework for Adaptive and Robust Aggregation in Federated Learning

Md Rafid Haque, Abu Raihan Mostofa Kamal, Md. Azam Hossain

机构 * Department of Computer Science and Engineering, Islamic University of Technology (IUT)（伊斯兰科技大学（IUT）计算机科学与工程系） 纠错

专题命中 规划决策 ：agent(abstract)；分类 cs.LG

Comments 24 pages, 8 figures. This work is intended for a journal submission

ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval

Nicola Fanelli, Gennaro Vessio, Giovanna Castellano

机构 * Department of Computer Science University of Bari Aldo Moro（计算机科学系巴里大学Aldo Moro） 纠错

专题命中 规划决策 ：agentic(abstract)