AI Agent - arXivDaily 专题

1109.1409 2012-04-30 cs.MA 82%

A georeferenced Agent-Based Model to analyze the climate change impacts on the Andorra winter tourism

M. Pons-Pons, P. A. Johnson, M. Rosas-Casals, B. Sureda, E. Jover

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

Comments 24 pages, 8 figures

1107.3225 2011-07-19 cs.MA 82%

An Agent-based Strategy for Deploying Analysis Models into Specification and Design for Distributed APS Systems

Luis Antonio de Santa-Eulalia, Sophie D'Amours, Jean-Marc Frayret

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

Comments In: International Journal of Computer Science Issues, Volume 8, Issue 3, May 2011, p.7-18, ISSN 1694-0814

cond-mat/0505581 2009-12-01 cond-mat.dis-nn 82%

Decision Making, Strategy dynamics, and Crowd Formation in Agent-based models of Competing Populations

K. P. Chan, Pak Ming Hui, Neil F. Johnson

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

Comments 14 pages, 3 figures, conference paper in WEHIA 2005

2608.11323 2026-08-13 cs.AI cs.LG 新提交 82%

Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations

部署决策可靠性：用于评估长 horizon 智能体规模的概化理论框架

Vasundra Srinivasan

机构 * Stanford School of Engineering（斯坦福工程学院）

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

AI总结该研究采用概化理论框架分析三个智能体基准的排行榜，发现其排名反映专业化而非能力，提出 DDR 报告规范并发布相关资源，为企业评估长 horizon 智能体提供可靠方法。

Comments 11 pages, 1 figure, 1 table. Code and reproducibility artifacts: https://github.com/vasundras/agent-reliability-engineering-lab

2607.14252 2026-07-17 cs.RO cs.AI cs.CL 新提交 82%

MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning

MEMORA：基于自我中心视频的具身动作记忆用于推理与规划

Zihao Yu, Xiu Yuan, Chongjie Zhang

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

AI总结研究针对长期机器人规划中对具身经验记忆的需求，提出MEMORA方法，通过形成-巩固-检索生命周期及四种类型存储实现具身动作记忆，经实验评估取得良好结果，能为机器人规划提供记忆上下文。

Comments 43 pages, 9 figures. Oral presentation at the Robotics: Science and Systems 2026 Workshop on Foundation Models for Robot Planning (FM4RoboPlan)

2607.10534 2026-07-14 cs.AI cs.CR cs.LG 新提交 82%

Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach

智能体技能中的跨层错位检测：一种渐进式加载感知对比学习方法

Chengjun Zhang, Yang Gao, Jianna Hur, Jingjing Zhang, Sagar Samtani

机构 * Indiana University Bloomington（印第安纳大学布卢明顿分校）

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

AI总结研究智能体技能跨层错位问题，提出渐进式加载感知分层对比学习框架PL-HCL，通过建模技能分层结构和学习跨层一致性来检测错位，使用相关语料库与挑战集，提升宏F1指标，为用户和运营商提供筛选工具与设计原则。

Comments 10 pages, 5 pages supplemental. Accepted at the KDD 2026 Workshop on Evaluation and Trustworthiness of Agentic AI

2606.09027 2026-06-09 cs.CL cs.AI 新提交 82%

SafeRun: Enabling Determinism in LLM Planning for Running

SafeRun：在跑步规划中实现LLM的确定性

Meilin Chen, Zepeng Zhai, Jiaxuan Zhao, Yuan Lu

机构 * University of California, Berkeley（加州大学伯克利分校）； Stanford University（斯坦福大学）

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

AI总结针对LLM在跑步规划中因概率性导致安全违规的问题，提出SafeRun框架，通过解耦架构将LLM的软解释与确定性求解器的硬约束分离，实现100%安全评分。

Comments Workshop on Planning in the Era of LLMs (LM4Plan) at ICML 2026

2604.15468 2026-04-24 cs.SE cs.AI 82%

The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE

半可执行堆栈：智能软件工程与SE范围的扩展

Robert Feldt, Per Lenberg, Julian Frattini, Dhasarathy Parthasarathy

机构 * Chalmers University of Technology（挑战者技术大学）； Volvo Group（沃尔沃集团）

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

AI总结本文探讨了软件工程领域因AI系统发展而扩展的范围，提出半可执行堆栈模型以分析可执行代码与非可执行 artifacts 的结合，通过三个案例研究重新定义工程目标，提供保留与净化的决策框架。

Comments This paper is the write-up of Robert Feldt's keynote "Agentic Software Engineering Will Eat the World: AI-Based Systems as the New Operating System of Society'' given at the Agentic Engineering 2026 workshop, Rio de Janeiro, Brazil, April 14, 2026. April 23 upload fixed the reference list to be more complete, and added a few additional citations; text essentially unchanged

2601.06102 2026-01-13 cs.AI cs.LG 82%

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems

动态智能上限：测量人工智能系统长期规划和创造力的长期限制

Truong Xuan Khanh, Truong Quynh Hoa

机构 * H&K Research Studio, Clevix LLC（Clevix LLC 研究室）

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

AI总结本文提出动态智能上限概念，通过轨迹导向评估框架量化人工智能系统长期规划与创造力的限制，揭示智能上限的动态性与轨迹依赖性。

Comments This paper introduces a trajectory-centric evaluation framework for analyzing long-horizon intelligence limits in artificial systems, focusing on developmental behavior, planning, and structural creativity rather than proposing new learning algorithms. 11 pages, 2 figures

2512.24014 2026-01-01 cs.CL cs.AI 82%

iCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning

iCLP: 基于隐式认知潜在规划的大语言模型推理

Sijia Chen, Di Niu

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； University of Alberta（阿尔伯塔大学）

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

AI总结 iCLP通过隐式认知潜在规划提升大语言模型的推理准确性和效率，实现跨领域泛化与可解释性。

Comments 9 pages, 6 figures. The source code is publicly available at https://github.com/AgenticFinLab/latent-planning

2510.16774 2025-10-21 cs.LG cs.AI 82%

Learning to play: A Multimodal Agent for 3D Game-Play

Yuguang Yue, Irakli Salia, Samuel Hunt, Christopher Green, Wenzhe Shi, Jonathan J Hunt

机构 * Player2

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

Comments International Conference on Computer Vision Workshop on Multi-Modal Reasoning for Agentic Intelligence

2502.06258 2025-08-05 cs.CL cs.LG 82%

Emergent Response Planning in LLMs

Zhichen Dong, Zhanhui Zhou, Zhixuan Liu, Chao Yang, Chaochao Lu

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

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

Comments Published at ICML 2025. Code available at: https://github.com/niconi19/Emergent-Response-Planning-in-LLMs

Journal ref Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)

2506.02351 2025-06-04 cs.CL cs.AI cs.CV 82%

DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization

Jeonghun Kang, Soonmok Kwon, Joonseok Lee, Byung-Hak Kim

机构 * Seoul National University（首尔国立大学）； CJ Corporation（CJ公司）

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

Comments To appear in the First REALM (Research on Agent Language Models) workshop at ACL 2025

2411.01639 2025-04-18 cs.RO cs.AI cs.CV cs.LG 82%

Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework

Neel P. Bhatt, Yunhao Yang, Rohan Siva, Daniel Milan, Ufuk Topcu, Zhangyang Wang

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

Comments Fine-tuned models, code, and datasets are available at https://uncertainty-in-planning.github.io/

2409.19924 2024-10-15 cs.AI cs.LG cs.RO 82%

On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability

Kevin Wang, Junbo Li, Neel P. Bhatt, Yihan Xi, Qiang Liu, Ufuk Topcu, Zhangyang Wang

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

Comments Code available at https://github.com/VITA-Group/o1-planning

2405.15019 2024-08-19 cs.RO cs.AI cs.LG 82%

Agentic Skill Discovery

Xufeng Zhao, Cornelius Weber, Stefan Wermter

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

Comments Webpage see https://agentic-skill-discovery.github.io/

2406.01562 2024-06-04 cs.LG cs.AI 82%

A New View on Planning in Online Reinforcement Learning

Kevin Roice, Parham Mohammad Panahi, Scott M. Jordan, Adam White, Martha White

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

Comments Published in the Planning and Reinforcement Learning Workshop at ICAPS 2024. arXiv admin note: text overlap with arXiv:2206.02902

2310.10625 2023-10-17 cs.CV cs.AI cs.LG cs.RO 82%

Video Language Planning

Yilun Du, Mengjiao Yang, Pete Florence, Fei Xia, Ayzaan Wahid, Brian Ichter, Pierre Sermanet, Tianhe Yu, Pieter Abbeel, Joshua B. Tenenbaum, Leslie Kaelbling, Andy Zeng, Jonathan Tompson

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

Comments https://video-language-planning.github.io/

2309.08587 2023-09-22 cs.LG cs.AI cs.RO 82%

Compositional Foundation Models for Hierarchical Planning

Anurag Ajay, Seungwook Han, Yilun Du, Shuang Li, Abhi Gupta, Tommi Jaakkola, Josh Tenenbaum, Leslie Kaelbling, Akash Srivastava, Pulkit Agrawal

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

Comments Website: https://hierarchical-planning-foundation-model.github.io/

2206.03674 2023-05-02 cs.LG cs.AI cs.RO 82%

Integrating Symmetry into Differentiable Planning with Steerable Convolutions

Linfeng Zhao, Xupeng Zhu, Lingzhi Kong, Robin Walters, Lawson L. S. Wong

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

Comments ICLR 2023 camera-ready version. Original name = "Integrating Symmetry into Differentiable Planning". Website: http://lfzhao.com/SymPlan

2303.14272 2023-03-28 cs.AI cs.LG cs.SC 82%

Learning to Operate in Open Worlds by Adapting Planning Models

Wiktor Piotrowski, Roni Stern, Yoni Sher, Jacob Le, Matthew Klenk, Johan deKleer, Shiwali Mohan

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

Comments To appears in the Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

2205.09991 2022-12-22 cs.LG cs.AI 82%

Planning with Diffusion for Flexible Behavior Synthesis

Michael Janner, Yilun Du, Joshua B. Tenenbaum, Sergey Levine

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

Comments ICML 2022 (long talk). Project page and code at https://diffusion-planning.github.io/

2109.15310 2022-03-22 cs.AI cs.LG 82%

Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari

Benjamin Ayton, Masataro Asai

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

Comments Accepted in ICAPS 2022, Planning & Learning track. Edits: Title change. Fixed the variance update formula. Updated the scores of $π$-IW as per authors' request. Included the results of DQN and EfficientZero

2102.03022 2021-02-08 cs.LG cs.AI cs.MA 82%

Deceptive Reinforcement Learning for Privacy-Preserving Planning

Zhengshang Liu, Yue Yang, Tim Miller, Peta Masters

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

Journal ref Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)

2010.01931 2020-10-06 cs.LG cs.AI 82%

Offline Learning for Planning: A Summary

Giorgio Angelotti, Nicolas Drougard, Caroline Ponzoni Carvalho Chanel

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

Comments 9 pages, ICAPS 2020 Conference - Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) Workshop

2003.03932 2020-03-10 cs.AI cs.LG 82%

Integrating Acting, Planning and Learning in Hierarchical Operational Models

Sunandita Patra, James Mason, Amit Kumar, Malik Ghallab, Paolo Traverso, Dana Nau

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

Comments Accepted in ICAPS 2020 (30th International Conference on Automated Planning and Scheduling)

1806.10792 2018-06-29 cs.LG cs.AI stat.ML 82%

Hierarchical Reinforcement Learning with Abductive Planning

Kazeto Yamamoto, Takashi Onishi, Yoshimasa Tsuruoka

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

Comments 7 pages, 6 figures, ICML/IJCAI/AAMAS 2018 Workshop on Planning and Learning (PAL-18)

1305.6129 2013-05-28 cs.LG cs.AI cs.MA cs.RO 82%

Information-Theoretic Approach to Efficient Adaptive Path Planning for Mobile Robotic Environmental Sensing

Kian Hsiang Low, John M. Dolan, Pradeep Khosla

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

Comments 19th International Conference on Automated Planning and Scheduling (ICAPS 2009), Extended version with proofs, 11 pages

1302.0723 2013-02-06 cs.LG cs.AI cs.MA cs.RO 82%

Multi-Robot Informative Path Planning for Active Sensing of Environmental Phenomena: A Tale of Two Algorithms

Nannan Cao, Kian Hsiang Low, John M. Dolan

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

Comments 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2013), Extended version with proofs, 15 pages

1101.5632 2011-02-01 cs.LG cs.AI cs.MA cs.RO 82%

Active Markov Information-Theoretic Path Planning for Robotic Environmental Sensing

Kian Hsiang Low, John M. Dolan, Pradeep Khosla

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

Comments 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), Extended version with proofs, 11 pages

1. 规划决策 35471 篇

A georeferenced Agent-Based Model to analyze the climate change impacts on the Andorra winter tourism

An Agent-based Strategy for Deploying Analysis Models into Specification and Design for Distributed APS Systems

Decision Making, Strategy dynamics, and Crowd Formation in Agent-based models of Competing Populations

Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations

MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning

Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach

SafeRun: Enabling Determinism in LLM Planning for Running

The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems

iCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning

Learning to play: A Multimodal Agent for 3D Game-Play

Emergent Response Planning in LLMs

DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization

Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework

On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability

Agentic Skill Discovery

A New View on Planning in Online Reinforcement Learning

Video Language Planning

Compositional Foundation Models for Hierarchical Planning

Integrating Symmetry into Differentiable Planning with Steerable Convolutions

Learning to Operate in Open Worlds by Adapting Planning Models

Planning with Diffusion for Flexible Behavior Synthesis

Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari

Deceptive Reinforcement Learning for Privacy-Preserving Planning

Offline Learning for Planning: A Summary

Integrating Acting, Planning and Learning in Hierarchical Operational Models

Hierarchical Reinforcement Learning with Abductive Planning

Information-Theoretic Approach to Efficient Adaptive Path Planning for Mobile Robotic Environmental Sensing

Multi-Robot Informative Path Planning for Active Sensing of Environmental Phenomena: A Tale of Two Algorithms

Active Markov Information-Theoretic Path Planning for Robotic Environmental Sensing