世界模型

Investigating Output Accuracy for a Discrete Event Simulation Model and an Agent Based Simulation Model

Mazlina Abdul Majid, Uwe Aickelin, Peer-Olaf Siebers

专题命中 仿真与规划 ：simulation model(title,abstract)；分类 cs.AI、cs.MA

Comments 5 pages, 4 figures, INFORMS Simulation Society Research Workshop

Journal ref Proceedings of the INFORMS Simulation Society Research Workshop, June 25-27, 2009, Warwick, UK, 101-105

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） 纠错

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.AI、cs.RO

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

Analytic Planning under Uncertainty with Moment Closure

基于矩闭合的不确定性下解析规划

Shishir Sharma, Doina Precup

机构 * McGill University（麦吉尔大学） ； Mila – Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所） 纠错

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

AI总结 本文提出一种基于矩闭合的不确定性下解析规划方法，通过二次动作值参数化实现闭式贝尔曼备份，在连续控制中降低目标方差，为感知分布的规划提供了合理框架。

Comments To appear in Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence (UAI 2026), PMLR

On Training in Imagination

在想象中训练

Nadav Timor, Ravid Shwartz-Ziv, Micah Goldblum, Yann LeCun, David Harel

机构 * Weizmann Institute of Science（魏茨曼研究所） ； New York University（纽约大学） ； Columbia University（哥伦比亚大学） ； New York University AMI Labs（纽约大学AMI实验室） 纠错

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.LG；dynamics model(abstract)

AI总结 研究在想象中训练方法中，动态和奖励模型误差对回报和策略优化的影响，提出最优样本分配和表示需求。

Model Space Reasoning as Search in Feedback Space for Planning Domain Generation

模型空间推理作为反馈空间中的搜索用于规划领域生成

James Oswald, Daniel Obolensky, Volodymyr Varha, Vasilije Dragovic, Kavitha Srinivas, Harsha Kokel, Michael Katz, Shirin Sohrabi

机构 * Rensselaer Polytechnic Institute（伦斯勒理工学院） ； IBM Research（IBM研究院） 纠错

专题命中 仿真与规划 ：world model(comments)；world models(comments)；分类 cs.AI；world model(comments)

AI总结 本文探讨了通过反馈空间中的启发式搜索优化规划领域生成的质量，利用符号反馈机制提升生成效果。

Comments Accepted at ICLR 2026 the 2nd Workshop on World Models: Understanding, Modelling and Scaling

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models

通过多步前驱模型缓解Dyna规划中的价值幻觉

Farzane Aminmansour, Taher Jafferjee, Ehsan Imani, Erin Talvitie, Micheal Bowling, Martha White

机构 * Dept of Computer Science, Harvey Mudd College, USA（美国哈维穆德学院计算机科学系） 纠错

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.AI、cs.LG

AI总结 本文提出通过多步前驱模型改进Dyna算法，以减少环境模型误差导致的价值幻觉问题，实验验证了该方法的有效性。

Comments Published in Journal of Artificial Intelligence (JAIR) in 2024. Updated to published version, changed title to JAIR version, added a new author that led the submission

SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games

SkyNet：基于信念的规划用于部分可观测随机博弈

Adam Haile

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI；dynamics model(abstract)

AI总结 SkyNet通过引入自我条件辅助头，改进了MuZero在部分可观测随机博弈中的规划能力，其在Skyjo游戏中实现了显著的胜率提升。

Environment Maps: Structured Environmental Representations for Long-Horizon Agents

环境地图：面向长周期智能体的结构化环境表示

Yenchia Feng, Chirag Sharma, Karime Maamari

机构 * Distyl AI 纠错

专题命中 仿真与规划 ：world model(comments)；world models(comments)；分类 cs.AI；world model(comments)

AI总结 本文提出环境地图，通过整合异构证据构建结构化图表示，提升长周期任务的鲁棒性。在WebArena基准上，环境地图使智能体成功率提升至28.2%，优于基线方法。

Comments 9 pages, 5 figures, accepted to ICLR 2026 the 2nd Workshop on World Models; updated formatting issue

SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding

SCALAR：通过LLM引导的符号规划和深度RL接地学习与组合技能

Renos Zabounidis, Yue Wu, Simon Stepputtis, Woojun Kim, Yuanzhi Li, Tom Mitchell, Katia Sycara

专题命中 仿真与规划 ：world model(comments)；world models(comments)；分类 cs.LG；world model(comments)

AI总结 SCALAR通过结合LLM引导的符号规划与深度RL，实现技能学习与组合，显著提升任务完成效率和鲁棒性。

Comments Best Paper Award Honorable Mention at NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning

Case-Guided Sequential Assay Planning in Drug Discovery

基于案例的药物发现顺序试验计划

Tianchi Chen, Jan Bima, Sean L. Wu, Otto Ritter, Bingjia Yang, Xiang Yu

机构 * Decision Science, Merck & Co., Inc., USA（决策科学，默克公司，美国） ； MSD Czech Republic（MSD捷克共和国） ； Pharmacokinetics, Dynamics, Metabolism & Bioanalytical, Merck & Co., Inc., USA（药代动力学、动力学、代谢与生物分析，默克公司，美国） 纠错

专题命中 仿真与规划 ：model-based RL(abstract)；分类 cs.AI、cs.LG

AI总结 IBMDP通过基于案例的隐式模型和集合MCTS规划，在无模拟器环境下实现高效药物发现实验顺序设计。

Inspection Planning Primitives with Implicit Models

基于隐式模型的检查规划原语

Jingyang You, Hanna Kurniawati, Lashika Medagoda

机构 * School of Computing, The Australian National University（澳大利亚国立大学计算学院） ； Abyss Solutions（Abyss解决方案） 纠错

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.AI、cs.RO

AI总结 本文提出基于隐式模型的检查规划原语，使基于采样的检查规划器能高效利用神经SDFs表示，减少内存使用并提升规划效率。

Bridging Tool Dependencies and Domain Knowledge: A Graph-Based Framework for In-Context Planning

Shengjie Liu, Li Dong, Zhenyu Zhang

机构 * Amazon（亚马逊） 纠错

专题命中 仿真与规划 ：world model(comments)；world models(comments)；分类 cs.AI；world model(comments)

Comments 4 pages, 2 figures, short paper, NeurIPS 2025 workshop on Bridging Language, Agent, and World Models for Reasoning and Planning

Can Image-To-Video Models Simulate Pedestrian Dynamics?

Aaron Appelle, Jerome P. Lynch

机构 * Duke University（杜克大学） 纠错

专题命中 仿真与规划 ：world model(comments)；world models(comments)；分类 cs.CV；world model(comments)

Comments Appeared in the ICML 2025 Workshop on Building Physically Plausible World Models, July 2025, https://physical-world-modeling.github.io/

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 仿真与规划 ：world model(comments)；world models(comments)；分类 cs.AI；world model(comments)

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

Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning

Yongshuai Liu, Xin Liu

机构 * University of California, Davis（加州大学戴维斯分校） 纠错

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies

Morgan Byrd, Jackson Crandell, Mili Das, Jessica Inman, Robert Wright, Sehoon Ha

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.LG、cs.RO

Comments Accepted to ICRA 2025. Website: https://morganbyrd03.github.io/icra25_privileged_dreamer/

Pre-Trained Video Generative Models as World Simulators

Haoran He, Yang Zhang, Liang Lin, Zhongwen Xu, Ling Pan

机构 * Hong Kong University of Science and Technology（香港科技大学） ； Tsinghua University（清华大学） ； Sun Yat-sen University（中山大学） ； Tencent AI Lab（腾讯AI实验室） 纠错

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.CV

Comments 20 pages

Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping

Bavo Lesy, Ali Anwar, Siegfried Mercelis

专题命中 仿真与规划 ：model-based RL(abstract)；分类 cs.AI、cs.LG

Comments 5 pages, 4 figures. Will be presented at IEEE RAAI 2024

A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings

Safa Alver, Doina Precup

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to EWRL 2024

Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning

Bradley Burega, John D. Martin, Luke Kapeluck, Michael Bowling

专题命中 仿真与规划 ：model-based RL(abstract)；分类 cs.AI、cs.LG

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 仿真与规划 ：model-based reinforcement learning(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

An Approach to Systematic Data Acquisition and Data-Driven Simulation for the Safety Testing of Automated Driving Functions

Leon Eisemann, Mirjam Fehling-Kaschek, Henrik Gommel, David Hermann, Marvin Klemp, Martin Lauer, Benjamin Lickert, Florian Luettner, Robin Moss, Nicole Neis, Maria Pohle, Simon Romanski, Daniel Stadler, Alexander Stolz, Jens Ziehn, Jingxing Zhou

专题命中 仿真与规划 ：分类 cs.AI、cs.LG、cs.CV；simulation model(abstract)

Comments 8 pages, 5 figures

Goal-Space Planning with Subgoal Models

Chunlok Lo, Kevin Roice, Parham Mohammad Panahi, Scott Jordan, Adam White, Gabor Mihucz, Farzane Aminmansour, Martha White

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

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 仿真与规划 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

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

HARPS: An Online POMDP Framework for Human-Assisted Robotic Planning and Sensing

Luke Burks, Hunter M. Ray, Jamison McGinley, Sousheel Vunnam, Nisar Ahmed

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.AI、cs.RO

Comments Accepted to IEEE Transactions on Robotics. 20 pages, 18 figures

Integration of Reinforcement Learning Based Behavior Planning With Sampling Based Motion Planning for Automated Driving

Marvin Klimke, Benjamin Völz, Michael Buchholz

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.LG、cs.RO

Comments 8 pages, 10 figures, to be published in 34th IEEE Intelligent Vehicles Symposium (IV)

Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning

Safa Alver, Doina Precup

专题命中 仿真与规划 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

Comments Published as a conference paper at CoLLAs 2023

Bridging the Gap Between Multi-Step and One-Shot Trajectory Prediction via Self-Supervision

Faris Janjoš, Max Keller, Maxim Dolgov, J. Marius Zöllner

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.AI、cs.RO

Comments 8 pages, 6 figures, to be published in 34th IEEE Intelligent Vehicles Symposium (IV)

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 仿真与规划 ：environment model(abstract)；分类 cs.AI、cs.LG

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

Safe Reinforcement Learning Using Black-Box Reachability Analysis

Mahmoud Selim, Amr Alanwar, Shreyas Kousik, Grace Gao, Marco Pavone, Karl H. Johansson

专题命中 仿真与规划 ：environment model(abstract)；分类 cs.LG、cs.RO

Comments This paper is accepted at IEEE Robotics and Automation Letters and International Conference on Robotics and Automation (ICRA)