Model-Based Planning

Follow this topic Ask about this topic

Model-based planning uses a model of how actions change the world to look ahead before acting, supporting decisions in robotics, navigation, games, tool use, and scheduling. Common approaches include model predictive control, Monte Carlo tree search and dynamic programming, symbolic action models, and learned latent or generative world models; language-model agents increasingly combine these with search, constraints, and execution feedback. Benchmarks range from simulated continuous control and manipulation to partially observable tasks, dynamic environments, and real-robot trials. A central challenge is that good predictions do not necessarily yield good plans: models must rank actions reliably over useful horizons while controlling computation, adapting to uncertainty and distribution shifts, and avoiding plans that exploit model errors.

Latest papers

208 papers40 papers in the last four weeks, up 33% on the four weeks before. 0.2% of all new papers.

Outcome-Aware Agents: When Does Causal Structure Help a Forward Model Foresee the Consequences of Actions?
Oct 25, 2026Mallesh MadapathiCausal World Models Action-Conditioned World Models
ThinkingDBx Pvt. Ltd., Hyderabad, India
Parameter Learning in Active Inference via Variational Message Passing
Oct 22, 2026Benedikt WaldeckActive Inference Model-Based Planning
University of Modena and Reggio Emilia, Italy
LLM-Based Exogenous World Modeling for Dynamic Scheduling
Oct 21, 2026Ni Zhang, Haofeng Yuan, Jianan Zhou +2Model-Based Planning Combinatorial Optimization
Singapore Management University · Tsinghua University · Nanyang Technological University
Exploring Temporal Context-Aware Physical Grounding in Latent World Models
Oct 20, 2026Yilei Man, Yang Chen, Jingcai GuoWorld Models Latent World Models
Department of Computing, The Hong Kong Polytechnic University · Department of Land Surveying and Geospatial Science, The Hong Kong Polytechnic University
Polyscene: Scenario Planning as Diversity Planning
Oct 20, 2026Mustafa F. Abdelwahed, Joan Espasa, Felipe MeneguzziModel-Based Planning
School of Computer Science, University of St Andrews, St Andrews · School of Natural and Computing Sciences, University of Aberdeen, Aberdeen
When Does an Added Planning Capability Create Operational Value? An Observable Evidence Standard
Oct 19, 2026Yihua Xu, Yan Lyu, Jize Li +4Policy Evaluation Model-Based Planning
Independent Researcher, San Jose, California, USA · Independent Researchers, Boston, Massachusetts, USA · Independent Researcher, Seattle, Washington, USA +2
VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching
Oct 19, 2026Yunzhe Hu, Dong XuOffline RL Model-Based Planning
School of Computing and Data Science, The University of Hong Kong
Train An Imaginative Agent
Oct 19, 2026Jiaxin Ge, Junyi Zhang, Tianning Chai +9LLM Agent Planning Model-Based Planning
University of California, Berkeley · Impossible Research · University of Washington +1
Long-Horizon Multi-Object Rearrangement via Distilled Tree Search over Continuous Actions
Oct 19, 2026Kallol Saha, Yining Hong, Amber Li +3Long-Horizon Robotic Manipulation Model-Based Planning
Robotics Institute, Carnegie Mellon University · Stanford University
ActTime: Action-Conditioned World Modeling for Time Series
Oct 19, 2026Xinxing Zhou, Xiaojie Yuan, Yanlong Wen +1Action-Conditioned World Models Model-Based Planning
Nankai University · Griffith University
Beyond Action Prediction: Learning Search-Free Planning in Latent Space
Oct 16, 2026Guanchen Du, Jinhao Du, Yanpeng Sun +3Latent-Space Planning Model-Based Planning
Nanjing University of Science and Technology · University of Oxford · Singapore University of Technology and Design +1
Learning Intrinsic Dynamics in Latent World Models
Oct 15, 2026Jiamin Shi, Yuanhong Zhang, Zhiyang Liu +2Latent Dynamics Modeling Latent World Models
Xi’an Jiaotong University · National University of Singapore · Beijing Zhongguancun Academy
One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models
Oct 14, 2026Joshua Cheung, Zhang HeLatent World Models World Model Evaluation
Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene
Oct 13, 2026Ruixiao Yang, Yilun Hao, Mingxin Yu +2Program Synthesis Model-Based Planning
MIT · MIT-IBM Watson AI Lab
Model-Based Online Decision Making via Generative Trajectory Planning
Oct 13, 2026Haldun Balim, Yilun Du, Na LiModel-Based Planning Model-Based RL
Harvard University
Scalable Robust MCTS with Anytime Deterministic Optimality Guarantees
Oct 11, 2026Tomer Massas, Vadim IndelmanRobust Markov Decision Processes Model-Based Planning
Faculty of Electrical and Computer Engineering, Technion – Israel Institute of Technology · Stephen B. Klein Faculty of Aerospace Engineering, Technion – Israel Institute of Technology · Faculty of Data and Decision Sciences, Technion – Israel Institute of Technology
CausalDreamer: Learning Predictive World Models with Latent Disentanglement
Oct 8, 2026Prince Jha, Nils Lukas, Kun Zhang +1World Model Learning Causal World Models
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Carnegie Mellon University
Predicted Futures Are Not Enough: Learning Executable Goals for Robot Manipulation
Oct 7, 2026Tzu-Yu Chuang, Ching-Hsiang Chang, Yi-Hsiu Lee +3Robotic Manipulation Robot Task Planning
National Yang Ming Chiao Tung University · National Tsing Hua University
Model-Based Geometry-Aware Generative Optimization for Constrained Locomotion Planning
Oct 6, 2026Zhilin He, Xinyuan Wang, Changliu LiuConstrained Generative Modeling Constrained Motion Planning
Carnegie Mellon University · University of Michigan, Ann Arbor
Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models
Oct 3, 2026Jinping Wang1, Zhiqiang Gao, Xiantong Zhen +1World Model-Based Planning World Model Learning
University of the Chinese Academy of Sciences · International Frontier Interdisciplinary Research Institute (IFIRI), Wenzhou-Kean University · OPI Labs
Learning Commute-Time-Preserving World Models for Planning
Oct 1, 2026Michael Hauri, Peter Buttaroni, Fabian A. Mikulasch +1Spectral Graph Embedding Representation Learning
Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland · Faculty of Science, University of Basel, Switzerland
SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents
Oct 1, 2026Ziwen Yu, Ivan Koychev, Elizabeth Coulthard +7Cost-Aware Inference Model-Based Planning
University of Bristol, Bristol, UK · Imperial College London, London, UK · Hunan Normal University, Changsha, China +1
Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
Oct 1, 2026Takumi Hara, Kanata SuzukiWorld Model Learning World Models for Robotics
Kyoto University Kyoto, Japan · Fujitsu Limited Kanagawa, Japan
In CEM, a World Model Is Also a Proposal Mechanism
Oct 1, 2026Oliver Obst, Frieder StolzenburgBlack-Box Optimization Model-Based Planning
UNSW Sydney · Harz University of Applied Sciences
JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
Sep 30, 2026Zheyuan Zhang, Suyu Ye, Nakul Agarwal +5Test-Time Adaptation Latent Dynamics Modeling
Honda Research Institute USA · Johns Hopkins University
Social-WM: Safety-Aware Latent World Models for Robot Social Navigation
Sep 30, 2026Zhihao Zheng, Mooi Choo ChuahWorld Models for Robotics World Model-Based Planning
Computer Science and Engineering department, P.C. Rossin College of Engineering and Applied Science, Lehigh University, Bethlehem, PA 18015, USA.
The Planning Limits of Latent World Models
Sep 30, 2026Ali Alrasheed, Basim Azam, Naveed AkhtarWorld Model-Based Planning Action-Conditioned World Models
The University of Melbourne, Australia
DeepJEPA: Scaling World Models from Within
Sep 30, 2026Zijian Jin, Yunbei Zhang, Yuanzhe Liu +5World Model Learning World Model-Based Planning
New York University · Tulane University · UIUC +4
Learning to Plan from Random Exploration
Sep 29, 2026Deqian Kong, Guangyan Sun, Sheng Cheng +6Long-Horizon Planning Model-Based Planning
UCLA · University of Minnesota · Amazon AGI +3
Anisotropic Representations Improve Planning in JEPA World Models
Sep 29, 2026Mingu Kang, Yoori Oh, Sookyung Kim +1Representation Learning World Model-Based Planning
Seoul National University · Ewha Womans University

Oct 25, 2026J/K move · Enter open · S save

Outcome-Aware Agents: When Does Causal Structure Help a Forward Model Foresee the Consequences of Actions?

Mallesh Madapathi

ThinkingDBx Pvt. Ltd., Hyderabad, India

Causal World Models Action-Conditioned World Models Model-Based Planning Causal Structure Learning

Open paper AskPDF arXiv

Agents that act on real systems should predict what their actions will cause before acting. We study when causal structure helps a learned forward model do this, using a planner that rejects candidate actions whose simulated multi-step outcome is unsafe, in synthetic structural causal models where the true consequences are known. We compare the Action-Conditioned Latent Structural Causal Model (AC-LSCM: per-factor mechanisms over a learned sparse graph, actions as do-interventions) with three unstructured forward models on seven random graphs with 10 or 20 variables, a task configured by a fixed rule, and two controls: a do-wrapper that gives every model the same action semantics, and counterfactual data given to all models or to none. When its factors are the observed variables, AC-LSCM recovers the true graph exactly on every 10-variable graph and has lower three-step prediction error than every baseline in all 396 paired comparisons. Its excess safety violations over an oracle are 0.25 of the no-model level on 10-variable graphs (best baseline 0.31) and 0.41 on 20-variable graphs (0.53), and its margin is largest for two-variable actions never seen in training (0.18 versus 0.28). With learned latent factors the same model is worse than the baselines; the choice of factors matters more than the explicit do-operator or counterfactual data, and every planner stays far from the oracle. This version corrects an earlier one, whose model learned an empty graph and whose headline 36x safety improvement came from a task that tested only extrapolation of action values; we withdraw that claim. Code and all per-seed results are released.