AI Agent

Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers

Jake Grigsby, Yuqi Xie, Justin Sasek, Steven Zheng, Yuke Zhu

专题命中 工具调用 ：agent(abstract)；分类 cs.LG

Comments Reinforcement Learning Conference 2025

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

Partially Observable Monte-Carlo Graph Search

Yang You, Vincent Thomas, Alex Schutz, Robert Skilton, Nick Hawes, Olivier Buffet

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

Comments To be published in Proceedings of ICAPS 2025

Differentiable Motion Manifold Primitives for Reactive Motion Generation under Kinodynamic Constraints

Yonghyeon Lee

机构 * Department of Mechanical Engineering, Massachusetts Institute of Technology（机械工程系，麻省理工学院） 纠错

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

Comments 6 pages and 9 figures

Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents

Thomas Banker, Ali Mesbah

机构 * Department of Chemical and Biomolecular Engineering, University of California, Berkeley, CA 94720, USA.（化学与生物分子工程系，加州大学伯克利分校） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.LG

On the Effectiveness of the z-Transform Method in Quadratic Optimization

Francis Bach

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

Learning to Move in Rhythm: Task-Conditioned Motion Policies with Orbital Stability Guarantees

Maximilian Stölzle, T. Konstantin Rusch, Zach J. Patterson, Rodrigo Pérez-Dattari, Francesco Stella, Josie Hughes, Cosimo Della Santina, Daniela Rus

机构 * CSAIL, Massachusetts Institute of Technology（CSAIL，麻省理工学院） ； Cognitive Robotics, Delft University of Technology（认知机器人学，代尔夫特理工大学） ； ELLIS Institute Tübingen（图宾根ELLIS研究所） ； Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所） ； Mechanical and Aerospace Engineering, Case Western Reserve University（机械与航空航天工程，凯斯西储大学） ； Division of Robotics, Perception and Learning, KTH（机器人、感知与学习部门，皇家理工学院） ； CREATE Lab, EPFL（CREATE实验室，瑞士联邦理工学院） ； Embodied AI AG, Lausanne, Switzerland（具身人工智能有限公司，瑞士洛桑） 纠错

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

Comments 73 pages

Scene-Aware Conversational ADAS with Generative AI for Real-Time Driver Assistance

Kyungtae Han, Yitao Chen, Rohit Gupta, Onur Altintas

机构 * InfoTech Labs, Toyota Motor North America（丰田北美信息科技实验室） 纠错

专题命中 工具调用 ：function calling(abstract)；分类 cs.AI

Reinforcement Learning for Automated Cybersecurity Penetration Testing

Daniel López-Montero, José L. Álvarez-Aldana, Alicia Morales-Martínez, Marta Gil-López, Juan M. Auñón García

机构 * Department of Artificial Intelligence and Big Data（人工智能与大数据系） ； GMV（GMV公司） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI

Doc2Agent: Scalable Generation of Tool-Using Agents from API Documentation

Xinyi Ni, Haonan Jian, Qiuyang Wang, Vedanshi Chetan Shah, Pengyu Hong

机构 * Michtom School of Computer Science（Michtom计算机科学学院） ； Brandeis University（布拉德雷大学） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.CL

Context-Aware Scientific Knowledge Extraction on Linked Open Data using Large Language Models

Sajratul Y. Rubaiat, Hasan M. Jamil

机构 * Department of Computer Science, University of Idaho（计算机科学系，爱达荷大学） 纠错

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

XPG-RL: Reinforcement Learning with Explainable Priority Guidance for Efficiency-Boosted Mechanical Search

Yiting Zhang, Shichen Li, Elena Shrestha

机构 * University of Michigan, Ann Arbor（密歇根大学） ； University of Illinois, Urbana-Champaign（伊利诺伊大学） 纠错

专题命中 工具调用 ：planning(abstract)；分类 cs.LG

Comments Accepted to RSS 2025 Workshop on Learned Robot Representations (RoboReps)

Magistral

Mistral-AI, :, Abhinav Rastogi, Albert Q. Jiang, Andy Lo, Gabrielle Berrada, Guillaume Lample, Jason Rute, Joep Barmentlo, Karmesh Yadav, Kartik Khandelwal, Khyathi Raghavi Chandu, Léonard Blier, Lucile Saulnier, Matthieu Dinot, Maxime Darrin, Neha Gupta, Roman Soletskyi, Sagar Vaze, Teven Le Scao, Yihan Wang, Adam Yang, Alexander H. Liu, Alexandre Sablayrolles, Amélie Héliou, Amélie Martin, Andy Ehrenberg, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Clémence Lanfranchi, Darius Dabert, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jean-Hadrien Chabran, Jean-Malo Delignon, Joachim Studnia, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Kush Jain, Lingxiao Zhao, Louis Martin, Luyu Gao, Lélio Renard Lavaud, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Maximilian Augustin, Mickaël Seznec, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patrick von Platen, Patryk Saffer, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Pavankumar Reddy Muddireddy, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Romain Sauvestre, Rémi Delacourt, Sanchit Gandhi, Sandeep Subramanian, Shashwat Dalal, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Thibault Schueller, Thibaut Lavril, Thomas Robert, Thomas Wang, Timothée Lacroix, Valeriia Nemychnikova, Victor Paltz, Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang, Yunhao Tang

专题命中 工具调用 ：function calling(abstract)；分类 cs.CL

A Heuristic Algorithm Based on Beam Search and Iterated Local Search for the Maritime Inventory Routing Problem

Nathalie Sanghikian, Rafael Meirelles, Rafael Martinelli, Anand Subramanian

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

Agile Reinforcement Learning for Real-Time Task Scheduling in Edge Computing

Amin Avan, Akramul Azim, Qusay Mahmoud

专题命中 工具调用 ：agent(abstract)；分类 cs.LG

Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain

Dimitris Panagopoulos, Adolfo Perrusquia, Weisi Guo

机构 * Faculty of Engineering and Applied Science, Cranfield University（工程与应用科学学院，克兰菲尔德大学） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI

Comments 6 pages, 2 figures, 3 tables, submitted as a regural paper to IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2025

Covering Number of Real Algebraic Varieties and Beyond: Improved Bounds and Applications

Yifan Zhang, Joe Kileel

机构 * Oden Institute, UT Austin（奥登研究所，德克萨斯大学奥斯汀分校） ； Department of Mathematics and Oden Institute, UT Austin（数学系和奥登研究所，德克萨斯大学奥斯汀分校） 纠错

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

Poster: libdebug, Build Your Own Debugger for a Better (Hello) World

Gabriele Digregorio, Roberto Alessandro Bertolini, Francesco Panebianco, Mario Polino

专题命中 工具调用 ：workflow(abstract)；分类 cs.SE

Journal ref CCS '24: Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security

Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization

Ruilong Wu, Xinjiao Li, Yisu Wang, Xinyu Chen, Dirk Kutscher

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

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

Solving the Pod Repositioning Problem with Deep Reinforced Adaptive Large Neighborhood Search

Lin Xie, Hanyi Li

机构 * Brandenburg University of Technology Cottbus-Senftenberg（勃兰登堡技术大学科特博-森芬堡） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI

Comments 14 pages, 2 figures, conference

lmgame-Bench: How Good are LLMs at Playing Games?

Lanxiang Hu, Mingjia Huo, Yuxuan Zhang, Haoyang Yu, Eric P. Xing, Ion Stoica, Tajana Rosing, Haojian Jin, Hao Zhang

机构 * UC San Diego（加州大学圣地亚哥分校） ； MBZUAI（穆桑贝斯人工智能研究院） ； UC Berkeley（加州大学伯克利分校） 纠错

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

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

Shelly Bensal, Umar Jamil, Christopher Bryant, Melisa Russak, Kiran Kamble, Dmytro Mozolevskyi, Muayad Ali, Waseem AlShikh

机构 * Writer, Inc.（Writer公司） 纠错

专题命中 工具调用 ：function calling(abstract)；分类 cs.CL

Proactive Guidance of Multi-Turn Conversation in Industrial Search

Xiaoyu Li, Xiao Li, Li Gao, Yiding Liu, Xiaoyang Wang, Shuaiqiang Wang, Junfeng Wang, Dawei Yin

机构 * Baidu Inc.（百度公司） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.CL

Comments ACL'25 (Industry)

VLM-RRT: Vision Language Model Guided RRT Search for Autonomous UAV Navigation

Jianlin Ye, Savvas Papaioannou, Panayiotis Kolios

机构 * KIOS Research and Innovation Centre of Excellence (KIOS CoE)（KIOS研究中心卓越创新中心） ； Department of Computer Science, University of Cyprus（计算机科学系，塞浦路斯大学） 纠错

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

Journal ref 2025 International Conference on Unmanned Aircraft Systems (ICUAS)

Automating Thought of Search: A Journey Towards Soundness and Completeness

Daniel Cao, Michael Katz, Harsha Kokel, Kavitha Srinivas, Shirin Sohrabi

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

Learning a Pessimistic Reward Model in RLHF

Yinglun Xu, Hangoo Kang, Tarun Suresh, Yuxuan Wan, Gagandeep Singh

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.LG

Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation

Yuelyu Ji, Rui Meng, Zhuochun Li, Daqing He

机构 * University of Pittsburgh（匹兹堡大学） ； Google Cloud AI Research（谷歌云人工智能研究） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.CL

SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL

Shuai Lyu, Haoran Luo, Ripeng Li, Zhonghong Ou, Jiangfeng Sun, Yang Qin, Xiaoran Shang, Meina Song, Yifan Zhu

机构 * School of Computer Science, Beijing University of Posts and Telecommunications, China（北京邮电大学计算机科学学院） ； College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院） ； State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China（北京邮电大学网络与交换技术国家重点实验室） ； College of Computer Science, Sichuan University, Chengdu, China（四川大学计算机学院） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI

Comments 28 pages,12 figures