arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

共收录 35686 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 规划决策 35686 篇

2503.17629 2025-12-23 cs.LG math.OC 83%

Planning and Learning in Average Risk-aware MDPs

在平均风险感知马尔可夫决策过程中的规划与学习

Weikai Wang, Erick Delage

机构 * GERAD & HEC Montréal(GERAD与蒙特利尔HEC学院) Mila - Québec AI Institute(魁北克AI研究所)

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

AI总结 本文提出了一种相对价值迭代算法和两种基于多级蒙特卡洛方法的Q学习算法,用于在平均风险感知马尔可夫决策过程中实现最优策略的收敛与识别。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17060 2025-12-22 cs.MA cs.AI 83%

On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialogues

在交易分析对话中LLM代理行为中情境信息和自我状态的作用

Monika Zamojska, Jarosław A. Chudziak

机构 * Faculty of Electronics and Information Technology(电子与信息技术学院) Warsaw University of Technology(华沙技术大学)

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

AI总结 本文提出了一种受交易分析理论启发的多代理系统,通过整合情境信息检索来增强LLM代理在交易分析对话中的行为真实性。

Comments Presented at the 39th Pacific Asia Conference on Language, Information and Computation (PACLIC 39)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17041 2025-12-22 cs.AI cs.SY eess.SY 83%

Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats

代理车辆的安全风险:对认知和跨层威胁的系统分析

Ali Eslami, Jiangbo Yu

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

AI总结 本文提出基于角色的架构,分析代理车辆中认知和跨层安全威胁,提供首个结构化分析框架。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.14886 2025-12-22 cs.CL 83%

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters

树状规划与理性化使大语言模型成为更好的辩论者

Danqing Wang, Zhuorui Ye, Xinran Zhao, Fei Fang, Lei Li

机构 * Carnegie Mellon University(卡内基梅隆大学)

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

AI总结 TreeDebater通过引入树状结构提升辩论策略,实现辩论说服力和胜率的显著提升。

Comments 9 main pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17116 2025-12-17 cs.AI 83%

MCTS-EP: Empowering Embodied Planning with Online Preference Optimization

MCTS-EP:通过在线偏好优化增强具身规划

Hang Xu, Zang Yu, Yehui Tang, Pengbo Hu, Yuhao Tang, Hao Dong

机构 * School of Management, Fudan University, Shanghai, China(复旦大学管理学院) Independent Researcher(独立研究者) CFCS, School of Computer Science, Peking University, Beijing, China(计算机科学系,北京大学) PKU-AgiBot Lab, Peking University, Beijing, China(北京大学)

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

AI总结 MCTS-EP通过结合大语言模型与蒙特卡洛树搜索,实现具身智能体的在线偏好优化,提升多模态任务的性能表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.10079 2025-12-17 cs.AI 83%

Reformulation Techniques for Automated Planning: A Systematic Review

用于自动规划的改写技术:系统综述

Diaeddin Alarnaouti, George Baryannis, Mauro Vallati

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

AI总结 本文系统综述了自动规划中改写技术的研究,旨在提供该领域全面视角并促进未来研究。

Comments Accepted and to appear in The Knowledge Engineering Review (KER), 2023

Journal ref The Knowledge Engineering Review 38 (2023) e9

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12716 2025-12-16 cs.CL 83%

CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning

CoDA:一种解耦的层次代理

Xuanzhang Liu, Jianglun Feng, Zhuoran Zhuang, Junzhe Zhao, Maofei Que, Jieting Li, Dianlei Wang, Hao Tong, Ye Chen, Pan Li

机构 * Georgia Institute of Technology(佐治亚理工学院) Alibaba Group(阿里巴巴集团)

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

AI总结 CoDA通过解耦的层次代理设计,利用强化学习有效缓解上下文爆炸问题,在复杂任务中实现性能提升。

Comments Accepted to WSDM '26 Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11270 2025-12-15 cs.AI 83%

A-LAMP: Agentic LLM-Based Framework for Automated MDP Modeling and Policy Generation

A-LAMP:基于代理的大型语言模型框架用于自动马尔可夫决策过程建模与策略生成

Hong Je-Gal, Chan-Bin Yi, Hyun-Suk Lee

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

AI总结 A-LAMP通过基于代理的大型语言模型自动将自然语言任务描述转换为马尔可夫决策过程并生成策略,提升了自动化建模和策略生成的效率与准确性。

Comments NeurIPS 2025 Workshop: Multi-Turn Interactions in Large Language Models. 26 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07533 2025-12-09 cs.CR cs.AI 83%

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection

VulnLLM-R:基于代理架构的专用推理LLM用于漏洞检测

Yuzhou Nie, Hongwei Li, Chengquan Guo, Ruizhe Jiang, Zhun Wang, Bo Li, Dawn Song, Wenbo Guo

机构 * Department of Computer Science, University of California, Santa Barbara, CA, USA(加州大学圣芭芭拉分校计算机科学系) Department of Computer Science, University of Chicago, Chicago, IL, USA(芝加哥大学计算机科学系) Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA(加州大学伯克利分校电子工程与计算机科学系) Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA(伊利诺伊大学厄巴纳-香槟分校计算机科学系)

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

AI总结 VulnLLM-R通过专用推理模型和代理架构,在漏洞检测中实现高效准确的AI驱动检测。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.10320 2025-12-09 cs.RO cs.AI 83%

MeshA*: Efficient Path Planning With Motion Primitives

MeshA*:基于运动原语的高效路径规划

Marat Agranovskiy, Konstantin Yakovlev

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

AI总结 MeshA*通过在网格单元格上搜索并拟合运动原语序列,实现高效路径规划,同时保证完整性和最优性,运行时间显著优于传统方法。

Comments Accepted to AAAI-2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08621 2025-12-08 cs.CL 83%

From Simulation to Strategy: Automating Personalized Interaction Planning for Conversational Agents

从模拟到策略:为对话代理自动化个性化交互规划

Wen-Yu Chang, Tzu-Hung Huang, Chih-Ho Chen, Yun-Nung Chen

机构 * Department of Computer Science and Information Engineering(计算机科学与信息工程系) National Taiwan University(台湾大学)

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

AI总结 本文提出了一种基于职业信息的轻量级策略,用于优化销售导向对话代理的个性化交互规划,通过调整对话意图提升对话效果。

Comments Accepted to IEEE ASRU 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04822 2025-12-05 cs.AI 83%

Enabling Ethical AI: A case study in using Ontological Context for Justified Agentic AI Decisions

实现道德AI:利用本体上下文进行合理化智能体决策的案例研究

Liam McGee, James Harvey, Lucy Cull, Andreas Vermeulen, Bart-Floris Visscher, Malvika Sharan

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

AI总结 本文提出一种协作人机AI方法,通过本体上下文构建可检查语义层,提升智能体决策的合理性和透明度。

Comments 24 pages including references, with 6 images and 2 tables. Appendices, supporting data and additional reference provided from page 25 to 117

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03931 2025-12-04 cs.AI 83%

Autonomous Agents and Policy Compliance: A Framework for Reasoning About Penalties

自主代理与政策合规:一种用于考虑处罚的推理框架

Vineel Tummala, Daniela Inclezan

机构 * Miami University(迈阿密大学)

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

AI总结 本文提出了一种基于逻辑编程的框架,用于政策感知的自主代理,通过引入惩罚机制提高决策的合规性和可解释性。

Comments 27 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02631 2025-12-03 cs.LG 83%

SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization

SeeNav-Agent: 通过视觉提示和分步策略优化增强视觉语言导航

Zhengcheng Wang, Zichuan Lin, Yijun Yang, Haobo Fu, Deheng Ye

机构 * Tencent AI Lab(腾讯AI实验室)

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

AI总结 SeeNav-Agent通过视觉提示和分步策略优化提升视觉语言导航性能,实验显示其在导航成功率上优于现有模型。

Comments 12 pages,6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00834 2025-12-02 cs.AI cs.NI 83%

SemAgent: Semantic-Driven Agentic AI Empowered Trajectory Prediction in Vehicular Networks

SemAgent:基于语义的代理AI赋能的车联网轨迹预测

Lin Zhu, Kezhi Wang, Luping Xiang, Kun Yang

机构 * State Key Laboratory of Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学) School of Intelligent Software and Engineering, Nanjing University (Suzhou Campus)(智能软件与工程学院,南京大学(苏州校区)) Department of Computer Science, Brunel University London(计算机科学系,布伦尔大学伦敦)

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

AI总结 SemAgent通过整合语义通信与代理AI,提升车联网环境下的轨迹预测性能,实验显示在低信噪比条件下预测精度提升达47.5%。

Comments Submitted for possible journal publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.22181 2025-12-01 cs.CV cs.AI cs.RO 83%

MTR-VP: Towards End-to-End Trajectory Planning through Context-Driven Image Encoding and Multiple Trajectory Prediction

MTR-VP: 通过基于上下文的图像编码和多轨迹预测实现端到端轨迹规划

Maitrayee Keskar, Mohan Trivedi, Ross Greer

机构 * Machine Intelligence, Interaction, and Imagination (Mi 3 ) Laboratory(机器智能、交互与想象实验室) University of California, Merced(加州大学默塞德分校) Laboratory for Intelligent & Safe Automobiles (LISA)(智能与安全汽车实验室) University of California, San Diego(加州大学圣地亚哥分校)

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

AI总结 MTR-VP通过基于上下文的图像编码和多轨迹预测实现端到端轨迹规划,利用交叉注意力提升规划性能。

Comments 8 pages, 3 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11043 2025-11-25 cs.AI cs.RO 83%

Autonomous Vehicle Path Planning by Searching With Differentiable Simulation

通过可微模拟进行自动驾驶路径规划

Asen Nachkov, Jan-Nico Zaech, Danda Pani Paudel, Xi Wang, Luc Van Gool

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

AI总结 本文提出DSS框架,利用可微模拟器Waymax进行路径规划,通过梯度下降优化动作序列,提升自动驾驶的跟踪和路径规划精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.10568 2025-11-24 cs.AI 83%

Observer-Aware Probabilistic Planning Under Partial Observability

感知-aware 的概率规划在部分可观测性下

Salomé Lepers, Vincent Thomas, Olivier Buffet

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

AI总结 本文提出了一种基于观察-aware 马尔可夫决策过程的框架,用于处理部分可观测性下的规划问题,通过优化信息传输来提升可解释性和可预测性。

Comments 23 pages, 13 figures. Complete version of AAMAS 2025 extended abstract

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16292 2025-11-21 cs.AI 83%

Distributed Agent Reasoning Across Independent Systems With Strict Data Locality

跨独立系统的分布式代理推理与严格数据本地性

Daniel Vaughan, Kateřina Vaughan

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

AI总结 本文提出了一种基于自然语言消息的分布式代理推理系统,通过伪匿名令牌和本地数据查询实现跨组织安全合作,验证了去中心化多代理系统的可行性。

Comments 27 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15456 2025-11-20 cs.AI q-fin.GN 83%

Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent Mining

了解您的意图:一种自主多视角大语言模型代理框架用于DeFi用户交易意图挖掘

Qian'ang Mao, Yuxuan Zhang, Jiaman Chen, Wenjun Zhou, Jiaqi Yan

机构 * Nanjing University(南京大学) The University of Tennessee, Knoxville(田纳西大学)

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

AI总结 本文提出TIM框架,通过多视角LLM代理系统挖掘DeFi用户交易意图,提升意图推断的准确性和可验证性。

Comments Written in 2025 Q1

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14446 2025-11-19 cs.CV cs.AI 83%

Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding

Hong Gao, Yiming Bao, Xuezhen Tu, Yutong Xu, Yue Jin, Yiyang Mu, Bin Zhong, Linan Yue, Min-Ling Zhang

机构 * SouthEast University(东南大学) ZTE Corporation(中兴通讯)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13361 2025-11-18 cs.AI cs.MA 83%

MedDCR: Learning to Design Agentic Workflows for Medical Coding

Jiyang Zheng, Islam Nassar, Thanh Vu, Xu Zhong, Yang Lin, Tongliang Liu, Long Duong, Yuan-Fang Li

机构 * Oracle Health and AI(Oracle健康与AI) Sydney AI Center, The University of Sydney(悉尼AI中心,悉尼大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13293 2025-11-18 cs.AI 83%

Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval

Chuang Zhao, Hui Tang, Hongke Zhao, Xiaofang Zhou, Xiaomeng Li

机构 * Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology(电子与计算机工程系,香港科技大学) College of Management and Economics, Laboratory of Computation and Analytics of Complex Management Systems (CACMS), Tianjin University(管理学院与经济学学院,复杂管理系统的计算与分析实验室,天津大学) Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(计算机科学与工程系,香港科技大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14557 2025-11-18 cs.AI cs.MA cs.RO 83%

Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles

Rhys Howard, Nick Hawes, Lars Kunze

机构 * Oxford Robotics Institute, Dept. of Eng. Sci., University of Oxford(牛津大学机器人研究所)

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

Comments 8 Pages, 5 Figures, To be published in the Proceedings of the 2025 IEEE International Conference on Robotics & Automation, Initial upload of accepted paper

Journal ref 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09073 2025-11-18 cs.FL cs.AI cs.GT 83%

Good-for-MDP State Reduction for Stochastic LTL Planning

Christoph Weinhuber, Giuseppe De Giacomo, Yong Li, Sven Schewe, Qiyi Tang

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

Comments 16 pages including appendices, accepted to AAAI 2026; fixed some typoes

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05888 2025-11-14 cs.AI cs.IR 83%

Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planning

Sahil Bansal, Sai Shruthi Sistla, Aarti Arikatala, Sebastian Schreiber

机构 * SAP Labs(SAP实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09533 2025-11-13 cs.NI cs.AI 83%

Digital Co-Founders: Transforming Imagination into Viable Solo Business via Agentic AI

Farhad Rezazadeh, Pegah Bonehgazy

机构 * Hostelworld Group(Hostelworld集团) BrainOmega Technical University of Catalonia (UPC)(技术大学 of 加泰罗尼亚(UPC)) Yazd University(亚兹德大学)

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

Comments 13 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06791 2025-11-11 cs.LG cs.MA 83%

Coupling Agent-based Modeling and Life Cycle Assessment to Analyze Trade-offs in Resilient Energy Transitions

Beichen Zhang, Mohammed T. Zaki, Hanna Breunig, Newsha K. Ajami

机构 * Lawrence Berkeley National Laboratory(伯克利劳伦斯国家实验室)

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

Comments 4 pages (+4 pages in appendix), 3 figures (+ 2 figures in appendix), 8 tables in appendix, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03773 2025-11-11 cs.AI 83%

Scaling Agent Learning via Experience Synthesis

Zhaorun Chen, Zhuokai Zhao, Kai Zhang, Bo Liu, Qi Qi, Yifan Wu, Tarun Kalluri, Sara Cao, Yuanhao Xiong, Haibo Tong, Huaxiu Yao, Hengduo Li, Jiacheng Zhu, Xian Li, Dawn Song, Bo Li, Jason Weston, Dat Huynh

机构 * Meta Superintelligence Labs(Meta超智能实验室) FAIR at Meta(Meta的FAIR部门) University of Chicago(芝加哥大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05528 2025-11-11 cs.AI 83%

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Aayush Aluru, Myra Malik, Samarth Patankar, Spencer Kim, Kevin Zhu, Sean O'Brien, Vasu Sharma

机构 * Algoverse AI Research(Algoverse AI研究)

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

Comments Multi-Turn Interactions in Large Language Models (MTI-LLM) Workshop at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏