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 93149 篇信号源：cs.AI, cs.CL, cs.LG, cs.SE

1. 规划决策 35504 篇

2403.17246 2025-03-27 cs.AI cs.CL cs.MA cs.RO 92%

TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models

David Bai, Ishika Singh, David Traum, Jesse Thomason

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

Comments 14 pages

2409.20560 2025-03-14 cs.RO cs.AI cs.CV cs.LG cs.MA 92%

LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner

Xiaopan Zhang, Hao Qin, Fuquan Wang, Yue Dong, Jiachen Li

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

Comments IEEE Conference on Robotics and Automation (ICRA 2025); Project website: https://lamma-p.github.io/

2410.02189 2025-03-12 cs.AI cs.LG cs.MA 92%

Agent-Oriented Planning in Multi-Agent Systems

Ao Li, Yuexiang Xie, Songze Li, Fugee Tsung, Bolin Ding, Yaliang Li

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

Comments Accepted by ICLR'2025

2412.02057 2025-02-25 cs.LG cs.AI cs.CY 92%

Comparative Analysis of Multi-Agent Reinforcement Learning Policies for Crop Planning Decision Support

Anubha Mahajan, Shreya Hegde, Ethan Shay, Daniel Wu, Aviva Prins

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

2312.02522 2024-12-03 cs.LG cs.AI cs.RO 92%

MASP: Scalable GNN-based Planning for Multi-Agent Navigation

Xinyi Yang, Xinting Yang, Chao Yu, Jiayu Chen, Wenbo Ding, Huazhong Yang, Yu Wang

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

Comments Submitted to IEEE RA-L

2405.11778 2024-05-21 cs.LG cs.AI cs.MA 92%

Efficient Multi-agent Reinforcement Learning by Planning

Qihan Liu, Jianing Ye, Xiaoteng Ma, Jun Yang, Bin Liang, Chongjie Zhang

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

Comments ICLR2024

2306.06543 2023-11-07 cs.RO cs.AI cs.LG 92%

MANER: Multi-Agent Neural Rearrangement Planning of Objects in Cluttered Environments

Vivek Gupta, Praphpreet Dhir, Jeegn Dani, Ahmed H. Qureshi

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

Comments The videos and supplementary material are available at https://sites.google.com/view/maner-supplementary

Journal ref Published in IEEE Robotics and Automation Letters, vol. 8, no. 12, pp. 8295-8302, Dec. 2023

2311.00063 2023-11-02 cs.RO cs.AI cs.LG cs.MA cs.SY eess.SY 92%

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning

Sleiman Safaoui, Abraham P. Vinod, Ankush Chakrabarty, Rien Quirynen, Nobuyuki Yoshikawa, Stefano Di Cairano

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

1905.12204 2023-08-15 cs.LG cs.AI cs.MA cs.RO stat.ML 92%

Learning NP-Hard Multi-Agent Assignment Planning using GNN: Inference on a Random Graph and Provable Auction-Fitted Q-learning

Hyunwook Kang, Taehwan Kwon, Jinkyoo Park, James R. Morrison

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

Journal ref Neural Information Processing Systems (NeurIPS) 2022

2306.08359 2023-06-16 cs.AI cs.LG 92%

Hierarchical Task Network Planning for Facilitating Cooperative Multi-Agent Reinforcement Learning

Xuechen Mu, Hankz Hankui Zhuo, Chen Chen, Kai Zhang, Chao Yu, Jianye Hao

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

2302.04376 2023-02-10 cs.LG cs.AI stat.ML 92%

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning

Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári

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

2301.08451 2023-01-23 cs.AI cs.LG cs.MA cs.RO 92%

Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimality

Chenning Yu, Qingbiao Li, Sicun Gao, Amanda Prorok

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

Comments Accepted by ICRA 2023

2203.10823 2022-03-22 cs.RO cs.AI cs.LG cs.MA 92%

Long Short-Term Memory for Spatial Encoding in Multi-Agent Path Planning

Marc R. Schlichting, Stefan Notter, Walter Fichter

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

Comments For associated source code, see https://github.com/MarcSchlichting/LSTMSpatialEncoding , For associated video of flight test, see https://schlichting.page.link/lstm_flight_test , 17 pages, 11 figures

Journal ref AIAA Journal of Guidance, Control, and Dynamics, March 2022

2110.01460 2021-10-05 cs.LG cs.AI 92%

Multi-Agent Path Planning Using Deep Reinforcement Learning

Mert Çetinkaya

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

2007.15724 2020-08-03 cs.RO cs.AI cs.LG cs.MA 92%

MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments

Zuxin Liu, Baiming Chen, Hongyi Zhou, Guru Koushik, Martial Hebert, Ding Zhao

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

Comments 6 pages, accepted at the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020)

2201.09467 2022-01-25 cs.MA cs.LG cs.RO 92%

CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces

Keisuke Okumura, Ryo Yonetani, Mai Nishimura, Asako Kanezaki

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

Comments To appear in the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022)

2110.02480 2021-10-07 cs.AI 92%

Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief

Christian Muise, Vaishak Belle, Paolo Felli, Sheila McIlraith, Tim Miller, Adrian R. Pearce, Liz Sonenberg

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

Comments Published in Special Issue of the Artificial Intelligence Journal (AIJ) on Epistemic Planning

2506.19592 2026-08-10 cs.AI cs.RO 92%

Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning

Harisankar Babu, Philipp Schillinger, Tamim Asfour

机构 * Bosch Center for Artificial Intelligence（博世人工智能中心）； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

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

Comments Accepted at IEEE CASE 2025, 8 pages, 8 figures

Journal ref 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), 2025, pp. 1701-1708

2606.23449 2026-06-23 cs.AI cs.OS 新提交 92%

AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction

AOHP：一个用于个性化、高效和安全交互的开源操作系统级Agent框架

Shanhui Zhao, Jiacheng Liu, Guohong Liu, Jichao Yan, Jialei Ye, Yuhao Yang, Hao Wen, Shizuo Tian, Yizhen Yuan, Yuxuan Chen, Yunxin Liu, Ju Ren, Ya-Qin Zhang, Chao Huang, Yao Guo, Yuanchun Li

机构 * Tsinghua University（清华大学）； Peking University（北京大学）； The University of Hong Kong（香港大学）

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

AI总结提出AOHP，一个基于AOSP的操作系统级Agent框架，通过将Agent视为一等OS参与者，实现个性化服务组合、高效Agent接口和安全信息流，在任务完成率、令牌成本和策略合规性上优于现有系统。

Comments 17 pages, 3 figures

2606.15141 2026-06-16 eess.AS cs.AI cs.SD 新提交 92%

EChO-Agent: Evidence Chain Orchestration Agent for Audio Reasoning

EChO-Agent: 用于音频推理的证据链编排智能体

Siyuan Zhang, Jian Zong, Junyu Wang, Peiyuan Jiang, Jiahao Yan, Jingyu Zhang, Tianrui Wang, Xiaobao Wang, Longbiao Wang, Jianwu Dang

机构 * School of Artificial Intelligence, Tianjin University（天津大学人工智能学院）

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

AI总结提出EChO-Agent模块化框架，将复杂音频问答转化为规划、工具执行、证据整合和答案验证流程，在MMAR基准上提升准确率和评分。

Comments 5 pages, 2 figures. Accepted by Interspeech 2026

2603.23838 2026-03-26 cs.AI cs.RO 92%

Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation

基于学习的优先规划在仓库自动化中的终身多智能体路径寻找

Han Zheng, Yining Ma, Brandon Araki, Jingkai Chen, Cathy Wu

机构 * Massachusetts Institute of Technology（麻省理工学院）

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

AI总结本文提出RL-RH-PP框架，结合强化学习与搜索规划，提升仓库自动化中多智能体路径寻找的效率与适应性。

Journal ref Journal of Artificial Intelligence Research, Vol. 85, Article 28. Publication date: March 2026

2603.02154 2026-03-11 cs.MA cs.AI 92%

Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning (Extended Version)

基于玻尔兹曼的探索用于鲁棒的去中心化多智能体规划（扩展版）

Nhat D. A. Nguyen, Duong D. Nguyen, Gianluca Rizzo, Hung X. Nguyen

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

AI总结本文提出CB-MCTS，通过玻尔兹曼策略和熵奖励提升多智能体规划的鲁棒性，在欺骗场景中表现更优。

Comments To appear in ICAPS 2026

2509.24230 2026-03-10 cs.AI cs.RO 92%

ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration

ELHPlan: 为多智能体协作的高效长周期任务规划

Shaobin Ling, Yun Wang, Chenyou Fan, Tin Lun Lam, Junjie Hu

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； City University of Hong Kong（香港城市大学）； South China Normal University（华南师范大学）

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

AI总结 ELHPlan通过引入意图绑定的动作链，实现多智能体协作中的高效长周期任务规划，提升适应性与效率，实验表明其在任务成功率与令牌消耗方面表现优异。

2602.17049 2026-03-02 cs.AI cs.HC cs.RO 92%

IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents

IntentCUA: 学习意图级表示以实现技能抽象和多智能体规划在计算机使用代理中

Seoyoung Lee, Seobin Yoon, Seongbeen Lee, Yoojung Chun, Dayoung Park, Doyeon Kim, Joo Yong Sim

机构 * Sookmyung Women's University（首尔女子大学）

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

AI总结 IntentCUA通过意图级表示和多智能体协作提升桌面自动化效率与稳定性。

Comments 12 pages, 9 figures, AAMAS 2026

2602.21670 2026-02-27 cs.RO cs.AI cs.MA 92%

Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning

分层基于大语言模型的多智能体框架与提示优化用于多机器人任务规划

Tomoya Kawabe, Rin Takano

机构 * Data Science Laboratories, NEC Corporation（日本电气株式会社数据科学实验室）

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

AI总结本文提出一种分层多智能体框架，结合提示优化提升多机器人任务规划的准确性和效率。

Comments Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2026. 8 pages, 2 figures

2510.11608 2026-02-17 cs.AI 92%

ParaCook: On Time-Efficient Planning for Multi-Agent Systems

ParaCook: 多智能体系统中高效时间规划的研究

Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang

机构 * Shanghai Jiao Tong University（上海交通大学）； University of California, Merced（加州大学梅尔德分校）

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

AI总结 ParaCook通过简化动作空间和烹饪任务实例化，为多智能体系统高效时间规划提供基准测试框架，评估LLMs在并行协调和高层次优化中的表现。

2508.12840 2026-02-09 cs.AI cs.MA 92%

Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics

通过GNN衍生启发式方法实现多智能体认知规划的扩展

Giovanni Briglia, Francesco Fabiano, Stefano Mariani

机构 * Department of Sciences and Methods for Engineering, University of Modena and Reggio Emilia（工程科学与方法系，摩德纳和雷吉奥艾米利亚大学）； Department of Computer Science, University of Oxford（计算机科学系，牛津大学）； Department of Computer Science, University of Pisa（计算机科学系，比萨大学）

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

AI总结本文通过GNN衍生启发式方法提升多智能体认知规划的可扩展性，改进求解效率。

2601.17346 2026-01-27 cs.AI 92%

Multi-Agent Learning Path Planning via LLMs

通过大型语言模型进行多智能体学习路径规划

Haoxin Xu, Changyong Qi, Tong Liu, Bohao Zhang, Anna He, Bingqian Jiang, Longwei Zheng, Xiaoqing Gu

机构 * Shanghai International Studies University（上海国际 Studies 大学）； East China Normal University（华东师范大学）； Huaiyin Normal University（淮阴师范学院）； City University of Macau（澳门城市大学）

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

AI总结本研究提出基于LLMs的多智能体学习路径规划框架，通过角色与规则协作机制提升学习路径的透明性与可解释性，实验表明其在路径质量、知识一致性及认知负荷匹配方面优于传统方法。

2601.14091 2026-01-21 cs.RO cs.AI 92%

Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems

零样本适应性任务规划用于自主建造机器人：轻量级单 agent 和多 agent 系统的比较研究

Hossein Naderi, Alireza Shojaei, Lifu Huang, Philip Agee, Kereshmeh Afsari, Abiola Akanmu

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

AI总结本研究通过比较轻量级单 agent 和多 agent 系统，探索了零样本适应性任务规划在自主建造机器人中的应用，展示了四 agent 团队在效率和成本上的优势。

2509.01022 2026-01-12 cs.AI cs.MA cs.RO 92%

Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned Agents

符号规划与在极度密集环境中无分配代理的多智能体路径寻找

Bo Fu, Zhe Chen, Rahul Chandan, Alex Barbosa, Michael Caldara, Joey Durham, Federico Pecora

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

AI总结本文提出五种基于搜索的算法，用于解决在极度密集环境中无分配代理的多智能体路径寻找问题，通过图搜索方法高效生成重新排列计划。

Comments AAAI Conference on Artificial Intelligence (AAAI-26)

↑