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 35394 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 规划决策 35394 篇

2510.03194 2025-10-06 cs.AI 87%

CoDA: Agentic Systems for Collaborative Data Visualization

Zichen Chen, Jiefeng Chen, Sercan Ö. Arik, Misha Sra, Tomas Pfister, Jinsung Yoon

机构 * Google Cloud AI Research(谷歌云人工智能研究) University of California, Santa Barbara(加州大学圣巴bara分校)

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

Comments 31 pages, 6 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17978 2025-09-29 cs.AI cs.LO 87%

The STAR-XAI Protocol: A Framework for Inducing and Verifying Agency, Reasoning, and Reliability in AI Agents

Antoni Guasch, Maria Isabel Valdez

机构 * Ixent Games

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

Comments Version 2: This article consolidates and replaces a previous version to present the complete research in a single, comprehensive manuscript

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18787 2025-09-24 cs.AI 87%

The AGNTCY Agent Directory Service: Architecture and Implementation

Luca Muscariello, Vijoy Pandey, Ramiz Polic

机构 * Cisco Systems(思科系统)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10621 2025-07-16 cs.CR cs.AI cs.CY cs.GT 87%

Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats

Quanyan Zhu

机构 * Quanyan Zhu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.11140 2025-06-23 cs.CV cs.AI cs.MA 87%

Autonomous Computer Vision Development with Agentic AI

Jin Kim, Muhammad Wahi-Anwa, Sangyun Park, Shawn Shin, John M. Hoffman, Matthew S. Brown

专题命中 规划决策 :agentic(title,abstract);agent(abstract);planning(abstract);workflow(abstract)

Comments The paper is 13 pages long and contains 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22311 2025-05-29 cs.AI cs.CY cs.NI eess.SP 87%

From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications

Feibo Jiang, Cunhua Pan, Li Dong, Kezhi Wang, Octavia A. Dobre, Merouane Debbah

机构 * Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University(智能计算与语言信息处理湖南省重点实验室,湖南师范大学) National Mobile Communications Research Laboratory, Southeast University(国家移动通信研究实验室,东南大学) Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business(长沙人工智能社会实验室,湖南工业大学) Department of Computer Science, Brunel University London(伦敦布鲁内尔大学计算机科学系) Faculty of Engineering and Applied Science, Memorial University(纪念大学工程与应用科学学院) G Research Center, Khalifa University of Science and Technology(科技大学6G研究中心)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.18371 2024-12-30 cs.SE 87%

Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents

Kaiwen Ning, Jiachi Chen, Jingwen Zhang, Wei Li, Zexu Wang, Yuming Feng, Weizhe Zhang, Zibin Zheng

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.03546 2024-06-09 cs.AI 87%

NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds

Shivam Goel, Yichen Wei, Panagiotis Lymperopoulos, Klara Chura, Matthias Scheutz, Jivko Sinapov

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

Comments Accepted at AAMAS-2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.06067 2023-06-12 cs.AI cs.MA 87%

Combining a Meta-Policy and Monte-Carlo Planning for Scalable Type-Based Reasoning in Partially Observable Environments

Jonathon Schwartz, Hanna Kurniawati, Marcus Hutter

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

Comments 24 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
1110.0624 2011-10-05 cs.LO cs.AI cs.PL 87%

Autonomous Agents Coordination: Action Languages meet CLP(FD) and Linda

Agostino Dovier, Andrea Formisano, Enrico Pontelli

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.16411 2026-08-18 cs.SE cs.AI 新提交 87%

Towards Risk-free AI Agent Deployment

迈向无风险的AI智能体部署

Yintong Huo, Rangeet Pan, Abhik Roychoudhury

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

AI总结 针对LLM智能体部署的安全、合规等风险,本文提出以智能体轨迹为基础,将测试与调试作为系统性研究方向,提炼部署就绪检查表并指出需解决的开放性问题,推动可信智能体部署。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02734 2026-06-30 cs.AI cs.CL 87%

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

CostBench:评估LLM工具使用代理在动态环境中的多轮成本最优规划与适应

Jiayu Liu, Cheng Qian, Zhaochen Su, Qing Zong, Shijue Huang, Bingxiang He, Yi R. Fung

机构 * Hong Kong University of Science and Technology(香港科技大学) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Tsinghua University(清华大学)

专题命中 规划决策 :planning(title,abstract);tool-use(title);分类 cs.AI、cs.CL

AI总结 本文提出CostBench,一个以成本为中心的可扩展基准,用于评估LLM代理在动态环境中的经济推理和重新规划能力,揭示现有模型在成本感知规划方面的显著不足。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23950 2026-05-26 cs.AI cs.SE 87%

Stop Comparing LLM Agents Without Disclosing the Harness

停止比较 LLM Agent 而不公开其执行框架

Yunbei Zhang, Janet Wang, Yingqiang Ge, Weijie Xu, Jihun Hamm, Chandan K. Reddy

机构 * Tulane University(Tulane 大学) Rutgers University(Rutgers 大学) Independent Researcher(独立研究者) Virginia Tech(弗吉尼亚理工大学)

专题命中 规划决策 :agent(title_cn,summary_cn);分类 cs.AI、cs.SE

AI总结 本文论证在长周期任务中,Agent 执行框架(Harness)比底层模型更能决定性能,并提出框架感知的评估标准与方差分解协议。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05963 2026-05-08 cs.AI cs.CL 87%

TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning

TheraAgent:自我改进的治疗剂用于精准且全面的治疗计划

Junkai Li, Yunghwei Lai, Tianyi Zhu, Zheng Long Lee, Weizhi Ma, Yang Liu

机构 * Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China(计算机科学与技术系,人工智能研究院,清华大学,北京,中国) Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China(人工智能产业研究院(AIR),清华大学,北京,中国) School of Computing, National University of Singapore, Singapore(计算学院,新加坡国立大学,新加坡)

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

AI总结 TheraAgent通过迭代生成-判断-改进流程提升治疗计划的精准度和完整性,实验显示其在HealthBench上表现优异,专家评估中胜率高达86%。

Comments Accepted to ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22154 2026-04-29 cs.AI cs.CL 87%

Exploring Reasoning Reward Model for Agents

探索用于智能体的推理奖励模型

Kaixuan Fan, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Zhixun Li, Yilei Jiang, Shuang Chen, Peng Pei, Xunliang Cai, Xiangyu Yue

机构 * MMLab, CUHK(CUHK 机器学习实验室) Meituan(美团) SEEM, CUHK(CUHK 系统工程与工程管理系)

专题命中 规划决策 :agent(summary_cn,abstract);tool use(abstract);agentic(abstract);分类 cs.AI、cs.CL

AI总结 本文提出Agent-RRM模型,通过结构化反馈提升智能体推理能力,采用三种集成策略在12个基准测试中取得显著性能提升。

Comments ACL 2026 Findings, Project page: https://github.com/kxfan2002/Reagent

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.15751 2025-12-19 cs.LG cs.AI cs.MA 87%

GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction

GLOW:基于图-语言协同推理的代理工作流性能预测

Wei Guan, Jian Cao, Jinyu Cai, Qiqi Cai, Jianqi Gao, See-Kiong Ng

机构 * School of Computer Science, Shanghai Jiao Tong University, China(上海交通大学计算机科学学院) Institute of Data Science, National University of Singapore, Singapore(新加坡国立大学数据科学研究所) School of Computer Engineering and Science, Shanghai University, China(上海大学计算机工程与科学学院)

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

AI总结 GLOW通过结合图神经网络与大语言模型,提出了一种统一的代理工作流性能预测框架,有效捕捉拓扑依赖和语义逻辑,提升预测准确性与排序效用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.07091 2025-10-09 cs.AI cs.CL 87%

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas

Baixuan Xu, Tianshi Zheng, Zhaowei Wang, Hong Ting Tsang, Weiqi Wang, Tianqing Fang, Yangqiu Song

机构 * The Hong Kong University of Science and Technology(香港科学与技术大学)

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

Comments 22 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07106 2025-08-01 cs.CL cs.AI 87%

Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models

Samir Abdaljalil, Hasan Kurban, Khalid Qaraqe, Erchin Serpedin

机构 * Texas A&M University(德克萨斯大学) Hamad Bin Khalifa University(哈马德·本·卡伊夫大学)

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

Comments ACL 2025 KnowFM

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.04893 2025-07-08 cs.AI cs.CL cs.MA 87%

MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction

Kaleem Ullah Qasim, Jiashu Zhang

机构 * School of Computing and Artificial Intelligence, Southwest Jiaotong University(计算机与人工智能学院,西南交通大学)

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

Comments 13 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.12555 2025-05-20 cs.HC cs.AI cs.CL 87%

PlanFitting: Personalized Exercise Planning with Large Language Model-driven Conversational Agent

Donghoon Shin, Gary Hsieh, Young-Ho Kim

机构 * University of Washington(华盛顿大学) NAVER AI Lab(NAVER人工智能实验室)

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

Comments 17 pages including reference. Accepted to ACM CUI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.11996 2023-06-27 cs.LG cs.AI 87%

K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs

Andrea Coletta, Svitlana Vyetrenko, Tucker Balch

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

Comments ICML 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.10655 2022-03-01 cs.SI cs.AI cs.CR cs.LG cs.MA 87%

Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning

Thai Le, Long Tran-Thanh, Dongwon Lee

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

Comments Accepted to The ACM Web Conference 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2012.10043 2021-03-02 cs.CV cs.AI cs.LG 87%

Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent

Peter Schaldenbrand, Jean Oh

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.11163 2024-02-20 cs.CL 87%

KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph

Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang Song, Chen Zhu, Hengshu Zhu, Ji-Rong Wen

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

Comments work in progress; efficient 7B LLM-based agent

详情

展开后加载摘要…

URL PDF HTML 收藏
2209.07758 2023-10-12 cs.RO cs.AI 87%

Game-theoretic Objective Space Planning

Hongrui Zheng, Zhijun Zhuang, Johannes Betz, Rahul Mangharam

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

Comments Submitted to 2024 International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23960 2026-08-07 cs.RO 版本更新 87%

Multi-Robot Motions in Milliseconds: Vector-Accelerated Primitives for Sampling-Based Planning

毫秒级多机器人运动:基于向量加速的采样规划原语

James D. Motes, Marco Morales, Nancy M. Amato

机构 * Parasol Lab, School of Computing and Data Science, University of Illinois at Urbana Champaign(帕索尔实验室,计算与数据科学学院,伊利诺伊大学厄巴纳-香槟分校) Department of Computer Science at Instituto Tecnológico Autónomo de México (ITAM)(墨西哥自治理工学院(ITAM)计算机科学系)

专题命中 规划决策 :planning(title,summary_cn)

AI总结 本文扩展了Vector-Accelerated Motion Planning框架,开发了多机器人MotionValidation和FindFirstConflict原语,利用SIMD并行性实现多机器人运动规划的高效验证与冲突检测,显著提升规划效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.05013 2026-08-06 cs.CL cs.AI cs.HC cs.LG cs.MA 新提交 87%

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

OneDayAgent:面向自主智能体的长程管控框架

Jingsheng Zheng, Xinyuan Fang, Jintian Zhang, Zhengke Gui, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University(浙江大学) Ant Group(蚂蚁集团)

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

AI总结 OneDayAgent是一种长程管控框架,可将开放式请求分解为子任务,在不同后端LLMs上实现最优性能,解决智能体的多类失效模式。

Comments Ongoing work

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03009 2026-08-05 cs.CR 新提交 87%

Tiny Enough to Break In: Agentic Remote Access Trojans Powered by Small Language Models

小到足以突破:由小型语言模型驱动的智能体远程访问木马

Yuhan You, Suhas Adavelly, Victoria Lovelace, Cameron Berryman, Joel Sadler, Daniel Graham

专题命中 规划决策 :agentic(title,summary_cn)

AI总结 该研究提出由小型语言模型(SLM)驱动的智能体远程访问木马(agentic RAT),经实验验证其架构可行,虽操作可靠性不足,但预示着AI驱动自主网络威胁的近现实风险。

Comments 6 pages, 5 figures, 1 table. Formatted in Springer LNCS style

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.02764 2026-08-05 cs.MA cs.DB 新提交 87%

Stateful Governance for Concurrent Agentic Systems

并发智能体系统的有状态治理

Yuxiang Peng, Xiaodi Wu

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

AI总结 本文针对并发智能体系统的有状态治理问题,提出Provenact运行时架构,可防止失效授权,在采购工作流中避免策略违规,为智能体框架的有状态治理提供了可行路径。

Comments 18 pages, 8 figures. Revision notes: system terminology updated; technical content and results unchanged

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.21804 2026-06-19 physics.ins-det hep-ex hep-ph 版本更新 87%

Agentic-AI Detector Co-design and Optimization in Vertically-Integrated Differentiable Full Simulations

Agentic-AI探测器协同设计与优化在垂直集成可微分全模拟中

Wonyong Chung, Qibin Liu, Liangyu Wu, Julia Gonski

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

AI总结 提出双层级优化框架,将AI智能体集成到高能物理探测器设计中,通过可微分全模拟联合优化几何、前端数字化和重建算法参数,在竞争性能指标下找到最优设计点。

Comments 7 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏