AI Agent

Learning and Planning with a Semantic Model

Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian

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

Comments submitted to ICLR 2019

Learning model-based planning from scratch

Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, Peter Battaglia

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

Simple Regret Optimization in Online Planning for Markov Decision Processes

Zohar Feldman, Carmel Domshlak

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

Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical World

自动策略，而非自动技能：面向物理世界的编译智能体技能

Zhonghao Zhan, Hamed Haddadi

机构 * Imperial College London（帝国理工学院） 纠错

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

AI总结 本文针对恶意智能体技能造成物理伤害的问题，提出位于技能制品内部的类型化权限层Edge Skillguard，可高效拒绝借用权限请求，验证了其在多场景下的防护效果。

Comments Presented at the 1st Workshop on Agent Skills (Agent Skills '26), ACM CAIS 2026, San Jose, May 26, 2026

Weather- and Location-Aware Agentic Dining Recommendation: Leveraging LLM World Knowledge for Region-Sensitive Contextual Reasoning

感知天气与位置的智能体餐饮推荐：利用大语言模型世界知识开展区域敏感语境推理

Kadharmoideen Fadurudeen

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

AI总结 该研究提出感知天气与位置的智能体餐饮推荐系统，利用LLM的世界知识生成区域敏感的适配天气的餐饮推荐，为智能体推荐提供了可扩展的架构模式。

Comments 5 pages. An agentic LLM system that reasons over combined location and weather context for region-sensitive dining recommendation. Working prototype implemented and briefly deployed end-to-end

AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles

AIvilization v0：迈向大规模人工社会模拟的统一代理架构与自适应代理档案

Wenkai Fan, Shurui Zhang, Xiaolong Wang, Haowei Yang, Tsz Wai Chan, Xingyan Chen, Junquan Bi, Zirui Zhou, Jia Liu, Kani Chen

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

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

AI总结 AIvilization v0通过统一代理架构和自适应代理档案，实现大规模人工社会模拟，解决目标稳定性与反应正确性矛盾，支持长周期自主性和多目标环境下的稳健性。

Comments v2: major revision. Agent architecture and environment consolidated into self-contained sections; new problem-setting section formalizing the asynchronous event model; evaluation reorganized by experiment with results reported alongside each protocol; added action-simulator audit, and human-steering analyses; other sections rewritten

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning

TREK：面向复杂行程规划的大语言模型智能体旅行推理与评估工具包

Jinhu Qi, Wentao Zhang, Siu Man Ng, Feiyang Xu, Yanyu Chen, Yaoman Li, Irwin King

机构 * The Chinese University of Hong Kong（香港中文大学） ； Macao Polytechnic University（澳门理工大学） 纠错

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

AI总结 本研究推出TREK旅行基准测试，解决现有行程规划智能体基准的不足，实验显示最强LLM智能体仅在不足五成任务生成可行计划，满足旅行者未明确需求是普遍瓶颈。

Comments Code, data, and evaluator: https://github.com/TonyQJH/TREK-A-Travel-Reasoning-and-Evaluation-Kit-for-LLM-Agents-in-Complex-Trip-Planning

Exploring Agentic Workflows for Generating High Quality Math Visual Aids

探索用于生成高质量数学视觉辅助工具的智能工作流程

Rizwaan Malik, Ashna Khetan, Isabel Sieh, Samin Khan

机构 * Stanford Graduate School of Education（斯坦福大学教育研究生院） ； Department of Computer Science（计算机科学系） 纠错

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

AI总结 研究针对中学数学图表可靠生成难的问题，引入智能工作流程，让 LLM 智能体评估并迭代改进生成的视觉效果，通过探索性评估确定改进关键领域，初步证明可提高 AI 生成数学图表的可靠性和教育价值。

Comments 13 pages, 9 figures. Exploratory course project on agentic workflows for generating and evaluating K 12 mathematical diagrams

FocalAD: Local Motion Planning for End-to-End Autonomous Driving

FocalAD：端到端自动驾驶中的局部运动规划

Bin Sun, Boao Zhang, Jiayi Lu, Xinjie Feng, Jiachen Shang, Rui Cao, Mengchao Zheng, Chuanye Wang, Shichun Yang, Yaoguang Cao, Ziying Song

机构 * School of Transportation Science and Engineering（交通科学与工程学院） ； State Key Lab of Intelligent Transportation System（智能交通运输系统国家重点实验室） ； Hangzhou International Innovation Institute（杭州国际创新研究院） ； School of Computer Science and Technolog（计算机科学与技术学院） ； Beijing Jiaotong University（北京交通大学） 纠错

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

AI总结 本文提出FocalAD框架，通过增强局部运动表示和关注关键局部邻居，提升自动驾驶的规划可靠性与鲁棒性，在nuScenes和Bench2Drive等数据集上表现优异。

Journal ref FocalAD: Local Motion Planning for End-to-End Autonomous Driving. Automot. Innov. (2026)

VeriGraph: Scene Graphs for Execution Verifiable Robot Planning

VeriGraph：用于可验证机器人规划的场景图

Daniel Ekpo, Mara Levy, Saksham Suri, Chuong Huynh, Archana Swaminathan, Abhinav Shrivastava

机构 * University of Maryland, College Park, MD USA（马里兰大学学院公园分校） 纠错

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

AI总结 VeriGraph通过整合视觉语言模型和场景图，提升机器人任务规划的可行性验证与修正，显著提高任务完成率。

Comments Accepted to ICRA 2026. Project website: https://verigraph-agent.github.io

WORKSWORLD: A Domain for Integrated Numeric Planning and Scheduling of Distributed Pipelined Workflows

WORKSWORLD：一个用于分布式流水线工作流集成数值规划和调度的领域

Taylor Paul, William Regli

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

AI总结 本文提出WORKSWORLD领域，用于永久调度工作流的数值无关规划器，通过定义数据源、组件和目标，解决联合规划与调度问题，实验证明在普通硬件上可处理最多14个组件的线性链工作流。

Comments To be published in Proceedings of the International Conference on Automated Planning and Scheduling Volume 36 (2026)

Interpretable Responsibility Sharing as a Heuristic for Task and Motion Planning

可解释的责任共享作为任务与运动规划的启发式方法

Arda Sarp Yenicesu, Sepehr Nourmohammadi, Berk Cicek, Ozgur S. Oguz

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

AI总结 本文提出了一种名为可解释责任共享（IRS）的新型启发式方法，用于提升家用机器人任务与运动规划的效率，通过利用人类构建的环境和固有偏见，结合辅助物体简化任务执行。

Comments Accepted for the Special Issue "Planning and Learning for Autonomous Robotics" in Robotics and Autonomous Systems

Socio-technical aspects of Agentic AI

群体技术视角下的代理AI

Praveen Kumar Donta, Alaa Saleh, Ying Li, Shubham Vaishnav, Kai Fang, Hailin Feng, Yuchao Xia, Thippa Reddy Gadekallu, Qiyang Zhang, Xiaodan Shi, Ali Beikmohammadi, Sindri Magnússon, Ilir Murturi, Chinmaya Kumar Dehury, Marcin Paprzycki, Lauri Loven, Sasu Tarkoma, Schahram Dustdar

机构 * Department of Computer and Systems Sciences, Stockholm University（斯德哥尔摩大学计算机与系统科学系） ； Center for Ubiquitous Computing, University of Oulu（奥卢大学无处不在计算中心） ； College of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院） ； Zhejiang A\&F University, Hangzhou（浙江工业大学之江学院） ； School of Computer Science, Peking University（北京大学计算机科学学院） ； Department of Mechatronics, University of Prishtina（普里什蒂纳大学机电系） ； Department of Computer Science, IISER Berhampur（伯尔哈普尔IISER计算机科学系） ； Systems Research Institute Polish Academy of Sciences（波兰科学院系统研究所） ； Department of Computer Science, University of Helsinki（赫尔辛基大学计算机科学系） 纠错

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

AI总结 本文从社会技术视角探讨代理AI，分析其技术组件与社会背景的关联，揭示伦理挑战及未来研究方向。

Comments Dear Reviewer, please note that this is not survey/review or position paper. This paper introduced new framework (MAD-BAD-SAD Framework) for Socio-technical aspects of Agentic AI, Ethical considerations, which is very important to consider beside technical development

Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance

可信AI在代理湖仓中的实现：从并发到治理

Jacopo Tagliabue, Federico Bianchi, Ciro Greco

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

AI总结 本文提出Bauplan设计，通过事务机制实现湖仓中的数据和计算隔离，解决代理工作流的可信性问题，并提供自修复管道的实现。

Comments AAAI26, pre-print of paper accepted at the Trustworthy Agentic AI Workshop

ExpertAgent: Enhancing Personalized Education through Dynamic Planning and Retrieval-Augmented Long-Chain Reasoning

Binrong Zhu, Guiran Liu, Nina Jiang

机构 * Department of Computer Science（计算机科学系） ； San Francisco State University（旧金山州立大学） ； Department of Mechanical & Industrial Engineering（机械与工业工程系） ； Louisiana State University（路易斯安那州立大学） 纠错

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

Comments Manuscript previously submitted to the NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models (LAW 2025)

Towards Zero-Shot, Controllable Dialog Planning with LLMs

Dirk Väth, Ngoc Thang Vu

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

Comments This paper has been accepted for publication at the AAAI 2022 Workshop on Planning in the Era of LLMs

Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings

Rushang Karia, Pulkit Verma, Alberto Speranzon, Siddharth Srivastava

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

Comments To appear at ICAPS-24

Journal ref Proceedings of the International Conference on Automated Planning and Scheduling, 34(1), 310-318, 2024

A Planning Ontology to Represent and Exploit Planning Knowledge for Performance Efficiency

Bharath Muppasani, Vishal Pallagani, Biplav Srivastava, Raghava Mutharaju, Michael N. Huhns, Vignesh Narayanan

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

Comments Ontology, Automated Planning, Planner Improvement

Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?

Nils Wilken, Lea Cohausz, Christian Bartelt, Heiner Stuckenschmidt

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

Comments Full publication: Wilken, N., Cohausz, L., Bartelt, C., Stuckenschmidt, H. (2023). Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?. In: Seipel, D., Steen, A. (eds) KI 2023: Advances in Artificial Intelligence. KI 2023. Lecture Notes in Computer Science(), vol 14236. Springer, Cham. arXiv admin note: text overlap with arXiv:2301.10571

A Reinforcement Learning-based Adaptive Control Model for Future Street Planning, An Algorithm and A Case Study

Qiming Ye, Yuxiang Feng, Jing Han, Marc Stettler, Panagiotis Angeloudis

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

Comments Proceeding for 57th ISOCARP World Planning Congress, Nov 8-11, 2021, Doha, Qatar

Guiding Robot Exploration in Reinforcement Learning via Automated Planning

Yohei Hayamizu, Saeid Amiri, Kishan Chandan, Keiki Takadama, Shiqi Zhang

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

Comments Accepted in International Conference of Planning and Scheduling (ICAPS-21)

Adaptive Informative Path Planning with Multimodal Sensing

Shushman Choudhury, Nate Gruver, Mykel J. Kochenderfer

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

Comments First two authors contributed equally; International Conference on Automated Planning and Scheduling (ICAPS) 2020

Planning Robot Motion using Deep Visual Prediction

Meenakshi Sarkar, Prabhu Pradhan, Debasish Ghose

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

Comments 7th ICAPS Workshop on Planning and Robotics (PlanRob), 2019

Probabilistic Planning by Probabilistic Programming

Vaishak Belle

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

Comments Article at AAAI-18 Workshop on Planning and Inference

Mixed Integer Linear Programming For Exact Finite-Horizon Planning In Decentralized Pomdps

Raghav Aras, Alain Dutech, François Charpillet

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

Journal ref Dans The International Conference on Automated Planning and Scheduling (2007)

AgenticER: the next frontier in Entity Resolution

AgenticER：实体解析的下一个前沿领域

George Papadakis, Panos Korovesis, Manolis Koubarakis, Themis Palpanas

专题命中 规划决策 ：agentic(summary_cn,abstract)；autonomous agent(abstract)

AI总结 针对现有实体解析被动范式无法适配异构流数据场景的问题，提出Agentic ER新范式，将其建模为自主智能体的序列决策过程，构建参考架构并明确研究挑战，开拓数据管理与智能体交叉的新研究方向。

Comments Vision paper submitted to VLDB, 6 pages

HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency

HEPTAPOD：编排高能物理工作流程以实现自主智能体

Tony Menzo, Alexander Roman, Sergei Gleyzer, Konstantin Matchev, George T. Fleming, Stefan Höche, Stephen Mrenna, Prasanth Shyamsundar

专题命中 规划决策 ：agent(abstract)；tool use(abstract)；planning(abstract)；workflow(abstract)

AI总结 研究针对高能物理工作流程，介绍HEPTAPOD编排框架，能集成外部大语言模型，使其与特定领域工具交互构建管理HEP管道，通过案例展示其能力，为高能物理中人工参与及智能体辅助工作流程奠定基础。

Comments 47 pages, 6 figures

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

VeriEvol：通过可验证的进化指令扩展多模态数学推理

Haoling Li, Kai Zheng, Jie Wu, Can Xu, Qingfeng Sun, Han Hu, Yujiu Yang

机构 * Tsinghua University（清华大学） ； Tencent Hunyuan（腾讯混元） 纠错

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

AI总结 提出VeriEvol框架，通过类型感知进化模块生成更难的问题，并利用HTV-Agent验证器确保答案可靠性，从而在强化学习中扩展多模态数学推理数据，提升模型性能。

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams

IPIBench: 在连续流下评估多模态大模型的交互式主动智能

Jinzhao Li, Yinuo Chen, Wenxuan Song, Yijia Lei, Yichi Zhang, Honglei Yan, Panwang Pan, Miao Liu

机构 * College of AI, Tsinghua University（清华大学人工智能学院） ； ByteDance（字节跳动） 纠错

专题命中 规划决策 ：agent(summary_cn,abstract)；agentic(abstract)

AI总结 提出IPIBench基准，用于评估多模态大模型在流式视频场景中的交互式主动智能，并设计IPI-Agent框架以改善主动触发和交互协调。

Heterogeneous Scientific Foundation Model Collaboration

异质科学基础模型协作

Zihao Li, Jiaru Zou, Feihao Fang, Xuying Ning, Mengting Ai, Tianxin Wei, Sirui Chen, Xiyuan Yang, Jingrui He

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 规划决策 ：agent(abstract)；planning(abstract)；agentic(abstract)；multi-agent(abstract)

AI总结 本文提出Eywa框架，通过将语言模型与领域特定基础模型结合，提升科学领域多模态任务的推理能力，实验显示其在结构化数据任务中表现更优。

Comments Preprint. 57 Pages