Model-Based Planning

Follow this topic Ask about this topic

Momentum

38 papers in the last four weeks, up 192% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 166

May 26, 2026cs.AI

Latent Goal Prediction from Language for Model-Based Planning

Planning with world models is bottlenecked by compounding prediction errors and the difficulty of defining optimizable goals. Visual targets provide precise local gradients but poor distant guidance, while language is flexible yet limited by noisy cross-modal alignment or dependence on large generative models unsuited for the high-sampling nature of model-based planning. To address these challenges, we introduce Latent Goal Prediction from Language (LAGO), a framework that predicts both sequences of intermediate goal states from language instructions and action-conditioned rollouts, all within the same latent space. Rather than optimizing toward a single global objective, LAGO dynamically decomposes instructions into explicitly predicted, locally tractable latent subgoals. By updating these subgoals online and using a soft minimum trajectory cost during planning, LAGO enables an agent to follow coherent latent trajectories over long horizons. Evaluation across multiple environments planning horizons shows that LAGO avoids the sharp degradation of prior methods. By achieving robust and precise long-horizon planning purely from language, LAGO bridges the precision of visual goals with the flexibility of text-guided control.

Samuel Barbeau, Simon Roy, Giovanni Beltrame +2

1École de Technologie Supérieure, Montréal · 2International Laboratory on Learning Systems (ILLS) · 3Polytechnique Montréal +4

World Model-Based Planning Long-Horizon Planning Model-Based Planning Latent World Models

May 25, 2026stat.ML

When Does LeJEPA Learn a World Model?

A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization) linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability, in a broad class of worlds where latents evolve under stationary, additive-noise transitions. Our main result is that among all such worlds, the Gaussian is the unique latent distribution for which this guarantee holds. The forward direction rests on a spectral decomposition in which each degree of nonlinearity is strictly penalized by alignment, making the linear map the optimum; the converse rules out every non-Gaussian alternative. We further prove an approximate identifiability result where the guarantee degrades gracefully, and show that linear, orthogonal identifiability enables optimal latent-space planning. We validate the theory with experiments ranging from 2D examples to 1024-dimensional latents, including distributional ablations and pixel-based robotic control. Our theory turns an empirically successful recipe into a mathematical guarantee, providing the foundation for building World Models that provably recover the structure of the world.

David Klindt, Yann LeCun, Randall Balestriero

Cold Spring Harbor Laboratory · New York University · Brown University

World Model Learning Representation Identifiability Parameter Identifiability Latent Dynamics Modeling Joint-Embedding Predictive Architecture Model-Based Planning

May 25, 2026cs.AI

Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations

World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are often either learned directly from pixels with limited semantic structure or inherited from frozen visual foundation models with excessive task-irrelevant detail, yielding state spaces that are poorly matched to downstream planning and control. This is especially challenging in reward-free offline settings, where the model must learn from fixed trajectories without reward supervision or online interaction. To address this, we propose TC-WM, a framework for turning foundation-model embeddings into compact, task-sufficient world representations. The key design is to treat the pretrained embedding space as a semantic scaffold rather than as the final state space: TC-WM linearly projects high-dimensional visual embeddings into a compact latent as the dynamic space, aligns a subspace with the agent's physical state via contrastive learning, and reconstructs embeddings to preserve useful visual structure. This combines the generality of foundation features with the controllability of task-centric dynamics. Theoretically, we show that TC-WM suffices to identify the underlying task-centric latent factors up to a simple transformation. Empirically, TC-WM enables test-time planning across diverse environments (e.g., Robomimic and D4RL), achieving better world-modeling quality and more precise control than state-of-the-art approaches.

Minghao Fu, Fan Feng, Nicklas Hansen +1

University of California, San Diego

World Model Learning World Models World Model-Based Planning Action-Conditioned World Models Offline RL Model-Based Planning+1

May 23, 2026cs.CV

Drift-Resistant Navigation World Model with Anchored Epipolar Guidance

We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models. Existing methods recursively feed generated content into subsequent steps, causing noise accumulation and degraded predictions, i.e., perceptual drift. Meanwhile, their predictions often deviate from the agent's motion, resulting in geometry drift. We address both types of drift by redesigning world-model prediction as an anchor-guided rollout. Instead of rolling out every frame sequentially, we first predict sparse future anchors that serve as stable long-range targets, and then generate intermediate frames within each chunk conditioned on both past context and future anchors. Importantly, these sparse anchors also provide geometric constraints, supported by bidirectional epipolar geometry, to localize where corresponding content should appear in the intermediate frames. Experiments on four benchmarks demonstrate consistent improvements over strong baselines in long-horizon visual quality, geometric consistency, and multi-view coherence. These gains further translate into improved downstream planning performance under the same planners, highlighting the importance of drift-resistant, geometry-aware prediction for reliable navigation world models.

Po-Chien Luan, Zimin Xia, Wuyang Li +2

World Models for Robotics Model-Based Planning Drifting Models Video World Models

May 23, 2026cs.RO

Can Predicted Dynamics Exist in the Physical World?

Can learned state-action proposals exist in the physical world? Before executing a proposed action sequence, a robot can inspect empirical variation and disagreement with a learned transition model. However, aggregating these diagnostic signals obscures whether a proposal is inconsistent with the predictor or merely departs from recorded behavior. We formalize this prediction-control interface, separate the scalar trigger from its channel-wise diagnostic log, and establish that an all-pairs displacement term is redundant within a maximum that already contains the corresponding one-step term. We evaluate the monitors on 700 nominal and 5,250 synthetically perturbed 32-transition PushT windows, observing only planar pusher positions and goals. The transition-RMSE baseline achieves a ROC-AUC of 0.982, compared with 0.957 for a heterogeneous maximum and 0.972 for a spread-scaled residual.

Barak Or

STATE16 Founder and CEO, STATE16

Robotic Control Model-Based Planning OOD Detection

May 22, 2026cs.AI

Neuro-Inspired Inverse Learning for Planning and Control

We present a neuro-inspired framework for embodied planning and control. Building on three principles that enable fast and highly effective goal-directed behavior in the mammalian brain - paired forward/inverse internal models, open-loop multi-step motor commands, and sequential, hierarchical organization of action - our Inverter framework uses learned components, trained end-to-end through Inverse Learning (IL) and supplemented where natural by analytic or algorithmic modules; we formalize IL and delineate it from supervised, reinforcement, and imitation learning. IL bridges Reinforcement Learning (RL)-style amortization, which runs in a single forward pass but emits only one action at a time, and Optimal Control (OC)-style sequence planning over whole trajectories, but with iterative test-time computation. Single Inverters or hierarchical n=2 Inverter stacks match or improve on offline-RL and diffusion-planner baselines on all 3 maze2d and 6 antmaze D4RL variants by an average of +24.2% (range -1.9% to +78.2%), at one-to-two orders of magnitude less inference compute time. Distinctively, optimizing through the Forward Model (FoM) over the entire T-step action sequence - rather than per step - lets Inverters produce smooth, goal-coherent, trajectory-wide structure and reach control policies closer to the analytic optimum than the policy underlying the training data itself. We also identify a failure mode of IL: FoM hacking under narrow training-data coverage, which we mitigate by using random training data with broader coverage. As an application example, a Pulse Inverter synthesizes arbitrary single-qubit quantum gates with fidelity matching the standard iterative numerical baseline (GRAPE), at more than 1000x lower per-gate compute time. In summary, we conclude that IL enables a versatile class of world-interfaces, especially for latency- and resource-critical embodied AI.

Maryna Kapitonova, Tonio Ball

NeuroMentum AI · IMBIT, University of Freiburg, Germany

Robot Policy Learning Model-Based Planning Model-Based RL

May 21, 2026cs.LG

World Model Control by Trajectory Reachability Metrics

Latent world models can learn representations that contain information needed for control, while the downstream controller may still rank candidate actions poorly when it relies on terminal latent distance alone. We study this failure in a fixed encoder and introduce trajectory reachability metrics (TRM), a small temporal pairwise cost trained from logged trajectories and used to rank predicted endpoints of a candidate action sequence against a goal. In the TwoRoom evaluation on 100 episodes from a high distance range, the original controller with LeWorldModel reaches 7.0% mean success. Temporal TRM trained after excluding all evaluation episodes reaches 96.7%, shuffled label controls stay at 0.0%, and TRM also improves PLDM from 32.7% to 84.0%. TopoNav, a separate pixel navigation task, shows the same link between repaired ranking and closed loop control. The selection audit with shared candidates (SASC) and rowspace interventions show that the gain comes from reweighting latent directions carrying the action decision. The XY rowspace contributes less than 1% of terminal latent MSE but carries most of the information needed for control. Coverage and boundary tests define the scope. Balanced doorway coverage restores a 0.0% coverage failure to 100.0% success, while an unseen wall orientation and contact rich PushT expose layout, dynamics, and recovery limits.

Liangyu Li, Shengzhi Wang, Libin Qiu +2

Tongji University

Reachability Analysis World Models for Robotics World Model-Based Planning Model-Based Planning Latent World Models

May 21, 2026cs.AI

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the presence, structure, or horizon of planning, these systems dramatically increase reasoning length, yielding inefficient token use without reliable accuracy gains. We argue efficient agentic reasoning benefits from decomposing decision-making into three systems: simulative reasoning (System II) grounding deliberation in future-state prediction via a world model; self-regulation (System III) deciding when and how deeply to plan via a learned configurator; and reactive execution (System I) handling fine-grained action. Simulative reasoning provides unified planning across diverse tasks without per-domain engineering, while self-regulation ensures the planner is invoked only when needed. To test this, we develop SR

^2

AM (Self-Regulated Simulative Reasoning Agentic LLM), realizing both as distinct stages within an LLM's chain-of-thought, with the LLM as world model. We explore two instantiations: recording decisions from a prompted multi-module system (v0.1) and reconstructing structured plans from traces of pretrained reasoning LLMs (v1.0), trained via supervised then reinforcement learning (RL). Across math, science, tabular analysis, and web information seeking, v0.1-8B and v1.0-30B achieve Pass@1 competitive with 120-355B and 685B-1T parameter systems respectively, while v1.0-30B uses 25.8-95.3% fewer reasoning tokens than comparable agentic LLMs. RL increases average planning horizon by 22.8% while planning frequency grows only 2.0%, showing it learns to plan further ahead rather than more often. More broadly, learned self-regulation instantiates a principle we expect to extend beyond planning to how agents govern their own learning and adaptation.

Mingkai Deng, Jinyu Hou, Lara Sá Neves +4

Carnegie Mellon University · Institute of Foundation Models (IFM)

LLM Planning World Model-Based Planning Agentic Reasoning Model-Based Planning LLM Agent Training LLM Agent Planning

May 17, 2026cs.RO

Visual Sculpting: Visually-Aligned Planning Representations for Long-Horizon Robot Clay Sculpting

Clay sculpting is a nuanced, artistic task involving dexterous manipulation with long-horizon planning to achieve high-level goals. As a robotics problem, we formulate clay sculpting as a shape-to-shape matching challenge. Prior deformable object manipulation work either requires retraining a policy per goal or relies on dynamics models which represent state as sparse point clouds which do not capture important clay features, such as textures, well. We present a method for modeling the dynamics of deformable materials and planning for robotic sculpting in a representation that is visually-aligned, capturing lighting and texture features. With three different deformable materials and various end-effectors, we demonstrate that our dynamics model is comparable in performance to the state-of-the-art with the added benefit of being compatible with visual planning. Our actions are represented as parametrized pushes into clay with a single end-effector, which proved to be suitable for long-horizon (>100 actions) clay relief sculptures. Lastly, we show the benefits of planning in a visually-aligned representation, but also provide analysis providing evidence as to why this representation is challenging to plan in compared to 3D representations.

Peter Schaldenbrand, Jean Oh

1The Robotics Institute, Carnegie Mellon University · 2Lavoro AI Research

Long-Horizon Robotic Manipulation Deformable Object Manipulation Long-Horizon Planning Robotic Manipulation Model-Based Planning Deformable Object Simulation

May 16, 2026cs.LG

Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning

The combination of exponentially large action spaces, stochastic dynamics, and long-horizon decision-making under limited resources makes Sequential Stochastic Combinatorial Optimization (SSCO) particularly challenging for reinforcement learning. Hierarchical Reinforcement Learning (HRL) offers a natural decomposition, but it places the high-level policy in a Semi-Markov Decision Process (SMDP) where actions have variable durations, making it difficult to learn a world model that is suitable for planning. We introduce a model-based hierarchical framework for sequential stochastic combinatorial decision-making that directly addresses this issue. Our method combines a latent-space tree-search planner with an SMDP-aware world model for variable-duration decisions. A multi-timescale objective structures the latent dynamics so that transition magnitudes reflect the effective temporal scales of abstract actions, enabling efficient lookahead under adaptive temporal abstraction. We further learn a subgoal-conditioned budget policy jointly with the world model to support context-aware resource allocation. Across challenging SSCO benchmarks, our method outperforms strong baselines.

Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen

Department of Electrical Engineering and Automation, Aalto University, Finland · Qutwo, Finland

World Model-Based Planning Hierarchical RL Combinatorial Optimization Model-Based Planning RL for Combinatorial Optimization Model-Based RL

May 15, 2026cs.AI

Imperfect World Models are Exploitable

We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred over another while the environment's true transition model implies the reverse. We analogize our definition with a prior characterization of reward hacking but show that the associated proof of inevitability does not transfer to exploitation. To overcome this obstruction, we develop a general theory of reward hacking and model exploitation that proves that exploitation is essentially unavoidable on large policy sets and yields the corresponding claim for hacking as a special case. Unfortunately, we also find that the conditions that guarantee unhackability in finite policy sets have no counterpart that precludes exploitation. Consequently, we introduce a relaxed notion of exploitation and derive a safe horizon within which it can be avoided. Taken together, our results establish a formal bridge between reward hacking and model exploitation and elucidate the limits of safe planning in world models.

Logan Mondal Bhamidipaty, Esmeralda S. Whitammer, David Abel +2

University of Edinburgh · Stanford University

Reward Hacking World Model-Based Planning Model-Based Planning Safe RL Model-Based RL

May 13, 2026cs.AI

Modeling Bounded Rationality in Drug Shortage Pharmacists Using Attention-Guided Dynamic Decomposition

Hospital pharmacists make high-stakes decisions to mitigate drug shortages under uncertainty, time pressure, and patient risk. Interviews revealed that pharmacists focus attention on a small subset of drugs, limiting cognitive effort to the most urgent cases. Motivated by these findings, we formalize a bounded-rational, attention-guided decision framework that dynamically decomposes drugs into a subset for high-cost reasoning and a complementary subset for low-cost monitoring. We develop two agents: an Expert Agent that applies attention weights derived from pharmacist interviews, and a Learner Agent that adapts attention allocation over time through experience. Across simulated scenarios spanning short to long horizons, we show that attention-guided planning supports stable decision-making without complete state reasoning. These results suggest that a primary decision is not what action to take, but where to allocate cognitive effort, and that attention-guided, satisficing strategies can reduce problem complexity while maintaining stable performance.

Yaniv Eliyahu Amiri, Noah Chicoine, Jacqueline Griffin +1

Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA · Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA, USA · Department of Psychology, Northeastern University, Boston, MA, USA

Computational Cognitive Modeling Clinical Decision-Making Model-Based Planning Bounded Rationality Decision-Making under Uncertainty

May 12, 2026cs.AI

State-Centric Decision Process

Language environments such as web browsers, code terminals, and interactive simulations emit raw text rather than states, and provide none of the runtime structure that MDP analysis requires. No explicit state space, no observation-to-state mapping, no certified transitions, and no termination criterion. We introduce the State-Centric Decision Process (SDP), a runtime framework that constructs these missing inputs by having the agent build them, predicate by predicate, as it acts. At each step the agent commits to a natural-language predicate describing how the world should look, takes an action to make it true, and checks the observation against it. Predicates that pass become certified states, and the resulting trajectory carries the four objects language environments do not provide, namely a task-induced state space, an observation-to-state mapping, certified transitions, and a termination criterion. We evaluate SDP on five benchmarks spanning planning, scientific exploration, web reasoning, and multi-hop question answering. SDP achieves the best training-free results on all five, with the advantage widening as the horizon grows. The certified trajectories additionally support analyses unavailable to reactive agents, including per-predicate credit assignment, failure localization, partial-progress measurement, and modular operator replacement.

Sungheon Jeong, Ryozo Masukawa, Sanggeon Yun +2

University of California, Irvine · 2Northeastern University

Markov Decision Processes Model-Based Planning

May 12, 2026cs.AI

Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs

We introduce missingness-MDPs (miss-MDPs), a novel subclass of partially observable Markov decision processes (POMDPs) that incorporates the theory of missing data. A miss-MDP is a POMDP whose observation function is a missingness function, specifying the probability that individual state features are missing (i.e., unobserved) at a time step. The literature distinguishes three canonical missingness types: missing (1) completely at random (MCAR), (2) at random (MAR), and (3) not at random (MNAR). Our planning problem is to compute near-optimal policies for a miss-MDP with an unknown missingness function, given a dataset of action-observation trajectories. Achieving such optimality guarantees for policies requires learning the missingness function from data, which is infeasible for general POMDPs. To overcome this challenge, we exploit the structural properties of different missingness types to derive probably approximately correct (PAC) algorithms for learning the missingness function. These algorithms yield an approximate but fully specified miss-MDP that we solve using off-the-shelf planning methods. We prove that, with high probability, the resulting policies are epsilon-optimal in the true miss-MDP. Empirical results confirm the theory and demonstrate superior performance of our approach over two model-free POMDP methods.

Joshua Wendland, Markel Zubia, Roman Andriushchenko +6

1Ruhr University Bochum · 2Brno University of Technology · 3Radboud University Nijmegen +2

Markov Models Learning with Missing Data Model-Based Planning Partially Observable Markov Decision Processes Decision-Making under Uncertainty

May 9, 2026cs.LG

Particle Monte Carlo Tree Search

Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement and action selection in Reinforcement Learning. Due to its sequential and deterministic nature, principled runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), a parallel MCTS algorithm which is suited for neural network evaluations, designed for GPU-acceleration with batch-parallelization and retains MCTS's principled approximate policy improvement interpretation. Empirically, PMCTS scales well with parallel compute and consistently outperforms or compares well to the popular heuristic-based baselines across a range of popular discrete- and continuous-action benchmark domains, including Chess, 19x19 Go, 9x9 Go, Gardner Chess, Snake, classical control environments from Brax and LLM reasoning in Sokoban.

Yaniv Oren, Viliam Vadocz, Joery A. de Vries +3

Department of Intelligent Systems, TU Delft · Centrum Wiskunde & Informatica, Amsterdam · Department of Computer Science, ETH Zürich +2

Monte Carlo Tree Search Model-Based Planning

May 9, 2026cs.RO

Latent Geometry Beyond Search: Amortizing Planning in World Models

Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging. This raises a central question: when does a learned representation simplify control, rather than merely enabling prediction? We study this question in a pretrained LeWorldModel, whose latent geometry is regularized for smoothness and uniformity. Our key insight is that, under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. We therefore replace iterative planning with a lightweight Goal-Conditioned Inverse Dynamics Model (GC-IDM) that maps the current latent state, goal latent state, and remaining horizon directly to the next action. Empirically, across four benchmark environments spanning navigation, contact-rich manipulation, and continuous control, our controller matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x. A broader sweep over test-time planners (CEM, MPPI, iCEM, and gradient-based methods) shows that this result is not specific to a particular optimizer. These findings suggest that much of the structure recovered by test-time planning is already locally encoded in the latent representation. More broadly, our results indicate that sufficiently structured latent spaces can shift part of the planning burden from online optimization to learned inference. Our code is publicly available at https://github.com/hdnndh/Latent-Geometry-Beyond-Search-Amortizing-Planning-in-World-Models .

Hoang Nguyen, Xiaohao Xu, Xiaonan Huang

Department of Robotics, University of Michigan, Ann Arbor

World Model-Based Planning Model-Based Planning Latent World Models Inverse Dynamics

May 8, 2026cs.LG

MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

Temporally contrastive representation learning induces a latent structure capable of reducing long-horizon planning to inference in a low-dimensional linear system. However, existing contrastive planning work learns a single latent geometry which cannot distinguish multiple valid behaviors trading task efficiency against risk exposure for the same start-goal query. We introduce MoMo, a preference-conditioned contrastive planner allowing a scalar user preference to continuously modulate plan conservativeness at inference time, without retraining. MoMo learns a joint conditioning of the representation geometry and latent prediction operator via Feature-Wise Linear Modulation and low-rank neural modulation, respectively. We show that our formulation preserves the probability density ratio encoded in the representation space that is required for inference-driven contrastive planning, further retaining its inference-time efficiency. Across six environments, MoMo smoothly adapts plan safety according to user preferences, yielding improved temporal and preferential consistency over state augmentation baselines.

Yusuf Syed, Viraj Parimi, Brian Williams

Massachusetts Institute of Technology

Contrastive Learning Model-Based Planning Decision-Making under Uncertainty

May 8, 2026cs.AI

Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration

Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However, in highly nonlinear and hybrid discrete-continuous domains, the resulting optimization landscapes are often ill-conditioned, with flat regions and sharp transitions that hinder effective optimization. We propose Model-Driven Policy Optimization (MDPO), a framework that introduces stochastic exploration into differentiable planning by injecting noise into the action space during optimization. Leveraging access to the model, MDPO further adapts the noise magnitude based on gradient-derived sensitivity of the trajectory objective, yielding a time-dependent exploration profile. This enables improved exploration of the objective landscape and helps escape poor local optima via dynamic allocation of exploration across timesteps and iterations. Experiments on benchmark domains demonstrate that MDPO consistently outperforms deterministic differentiable planning, including both the noise-free variant of our method and available state-of-the-art implementations, as well as model-free baselines such as PPO, significantly improving solution quality across challenging nonlinear and hybrid settings. We further analyze the evolution of the adaptive noise magnitude across both time steps and optimization iterations, providing insight into how exploration is allocated during learning.

Yuval Aroosh, Ayal Taitler

Department of Industrial Engineering and Management Ben-Gurion University of the Negev Beer Sheva, Israel

Policy Optimization RL Exploration Model-Based Planning

May 8, 2026cs.RO

Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models

World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions. However, the reliability of these imagined futures remains under-examined: is a generated future merely visually plausible, or is it dynamically compatible with the action sequence it claims to model? In this work, we identify action-state consistency, the alignment between predicted actions and induced state transitions, as a missing reliability axis for WAMs. Through a systematic study across representative joint-prediction and inverse-dynamics models, we find that action-state consistency systematically separates successful and failed rollouts across many tasks and follows similar success-failure trends as learned value estimates. These results suggest that consistency captures decision-relevant structure beyond visual realism. We further identify background collapse as an important boundary condition, where low-dynamics failed trajectories can become deceptively consistent because static futures are easier to predict. Building on these findings, we introduce a value-free consensus strategy for test-time selection, which ranks candidate rollouts by agreement among predicted futures. This strategy improves success rates on RoboCasa and RoboTwin 2.0 without additional training or reward modeling. Taken together, our findings establish action-state consistency as both a diagnostic tool for evaluating WAM reliability and a practical signal for value-free planning.

Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo +1

National Yang Ming Chiao Tung University

World Models for Robotics World Model-Based Planning Model-Based Planning World Action Models World Model Evaluation

May 8, 2026cs.LG

Predictive but Not Plannable: RC-aux for Latent World Models

A latent world model may achieve accurate short-horizon prediction while still inducing a latent space that is poorly aligned with planning. A key issue is spatiotemporal mismatch: these models are often trained with local predictive supervision, but deployed for long-horizon goal-directed search in latent spaces where Euclidean distance may not reflect what is reachable within a finite action budget. We present the Reachability-Correction auxiliary objective (RC-aux), a lightweight correction for this mismatch in reconstruction-free latent world models. RC-aux keeps the world-model backbone unchanged and adds planning-aligned supervision along two axes. Along the time axis, multi-horizon open-loop prediction trains the model beyond one-step consistency. Along the space axis, budget-conditioned reachability supervision, together with temporal hard negatives, encourages the latent space to distinguish states that are eventually reachable from those reachable within the current planning horizon. At test time, the learned reachability signal can also be used by a reachability-aware planner to favor trajectories that are both goal-directed and attainable under the available budget. We instantiate RC-aux on LeWorldModel and evaluate it under both continuation-training and matched-from-scratch settings. Across goal-conditioned pixel-control tasks and a LIBERO-Goal extension, RC-aux improves LeWM-style planning with modest additional cost. These results suggest that planning with latent world models depends not only on predictive accuracy, but also on whether the learned representation encodes the temporal and geometric structure required by downstream search. The code is available at https://github.com/Guang000/RC-aux.

Wenyuan Li, Guang Li, Keisuke Maeda +2

Hokkaido University

Reachability Analysis World Model-Based Planning Model-Based Planning Latent World Models

May 8, 2026cs.CV

See Tomorrow, Act Today: Foresight-Driven Autonomous Driving

Current end-to-end autonomous driving planners are fundamentally reactive: they condition on historical and present observations to predict future actions. We argue that autonomous agents should instead imagine future scenes before deciding, just as human drivers mentally simulate

what will happen next" before acting. We introduce ForeSight, a foundation world model centric planning framework that reframes autonomous driving as anticipatory decision-making. Rather than treating world models as auxiliary components, ForeSight makes future scene imagination the primary driver of action prediction. Our approach operates in two stages: (1) generating plausible future visual worlds via a pretrained world model, and (2) planning actions conditioned on these imagined futures. This paradigm shift from

what should I do now?" to ``what will happen, and how should I respond?" enables genuinely anticipatory rather than reactive planning. By grounding decisions in anticipated contexts rather than present observations alone, ForeSight navigates dynamic, interactive scenarios more effectively. Extensive experiments on NAVSIM and nuScenes demonstrate that explicit future imagination significantly outperforms previous state-of-the-art alternatives, validating our foresight-driven approach.

Bozhou Zhang, Nan Song, Yuang Wang +3

School of Data Science, Fudan University · Shanghai Innovation Institute · Imperial College London +1

End-to-End Autonomous Driving World Models World Model-Based Planning Model-Based Planning World Models for Autonomous Driving Autonomous Driving Planning

May 7, 2026cs.RO

When to Trust Imagination: Adaptive Action Execution for World Action Models

World Action Models (WAMs) jointly predict future visual observations and actions, but typically execute a fixed number of actions before replanning, regardless of whether the imagined future remains consistent with reality. We formulate adaptive WAM execution as future--reality verification and propose Future Forward Dynamics Causal Attention (FFDC), a lightweight verifier that reasons over predicted actions, predicted visual dynamics, real observations, and instruction-conditioned semantics. FFDC allows continued execution when a plan remains reliable and triggers replanning when its validity deteriorates. We combine verification with Mixture-of-Horizon Training to improve long-horizon trajectory coverage. On RoboTwin, FFDC-WAM achieves the highest average success rate among the evaluated methods in both clean and randomized settings. Under randomization, it improves success by 2.54 percentage points over Base-Motus while reducing WAM planning calls by 69.10% and completion time by 33.88%. Notably, across six real-world tasks on a Unitree G1D robot, FFDC-WAM improves average success by 9.17% over Base-Motus-LC16 while reducing calls by 74.06% and completion time by 51.31%.

Rui Wang, Yue Zhang, Canyang Chen +3

Southern University of Science and Technology, Shenzhen, China · The University of Hong Kong, Hong Kong, China

Long-Horizon Robotic Manipulation World Models for Robotics Action-Conditioned World Models Robot Task Planning Model-Based Planning World Action Models

May 7, 2026cs.AI

HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning

World models enable model-based planning through learned latent dynamics, but imagined rollouts become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability reflects two missing structures in planner-facing latents: history-conditioned memory for approximate Markov completeness, and geometric organization that separates configuration, momentum, and task semantics. We propose HaM-World (HMW), a structured world model that decomposes the latent state into a canonical (q, p) subspace and a context subspace c, while using Mamba selective state-space memory as the history-conditioned input to the same latent dynamics. Within this interface, (q, p) evolves through an energy-derived Hamiltonian vector field plus learnable residual/control dynamics, while c captures semantic, dissipative, and non-conservative factors. This gives the planner a single latent state shared by dynamics prediction, reward/value estimation, imagined rollouts, and CEM action search. On four DeepMind Control Suite tasks, HaM-World reaches the highest Avg. AUC (117.9, +9.5%), reduces long-horizon rollout error to 45% of a strong baseline model, and wins 11/12 k in {3,5,7} MSE cells. Under 12 OOD perturbations spanning dynamics shifts, action delay, and observation masking, HaM-World achieves the highest return in every condition, with average OOD-return gains of 10.2% on Finger Spin and 13.6% on Reacher Easy. Mechanism diagnostics further show bounded action-free Hamiltonian-energy drift, structured energy variation under policy rollouts, and coherent control-induced energy transfer, supporting the intended Soft-Hamiltonian dynamics design.

Haoyun Tang, Haodong Cui, Keyao Xu +2

1Xi’an Jiaotong University · 2Huazhong University of Science and Technology · 3Nankai University +1

World Model Learning Latent Dynamics Modeling World Model-Based Planning Hamiltonian Neural Networks Model-Based Planning Hamiltonian Dynamics

May 6, 2026cs.LG

Using Common Random Numbers for Simulation-based Planning with Rollouts

Simulation-based planning with rollouts is a widely-deployed technique for decision making in stochastic environments. The primary instrument of simulation-based planning is a sampling model, which is repeatedly called to generate trajectories and estimate the utilities of available actions. Among the actions thus explored, one with the maximum estimated utility is then executed. In this paper, we examine the effect of using common random numbers in the simulation process. We obtain a simple recipe for (provably) reducing variance in relative utility when simulations invoke a rollout policy beyond some depth. Experiments on synthetic tasks confirm that our scheme improves task performance. The broader significance of our innovation is apparent from two practical applications: (1) single-step lookahead planning in a pension-disbursement task, and (2) a deployment of the well-known UCT algorithm for the game of Ludo.

Sandarbh Yadav, Frederic J Maliakkal, Harshad Khadilkar +1

Department of Computer Science and Engineering, IIT Bombay, India

Monte Carlo Tree Search Model-Based Planning Variance Reduction

May 3, 2026cs.LG

TRAP: Tail-aware Ranking Attack for World-Model Planning

World models enable long-horizon planning by internally generating and evaluating imagined trajectories, making them a promising foundation for generalist agents. However, this imagination-driven decision process also introduces new security risks. Existing backdoor attacks typically aim to manipulate local features, one-step predictions, or instantaneous policy outputs. While such objectives may suffice for weaker reactive models, they are often ineffective against world models, where the learned dynamics prior and planning process can absorb or wash out the effects of shallow perturbations. More importantly, we find that world models exhibit a distinct backdoor vulnerability rooted in the long-tailed ranking structure of imagined trajectories, where disrupting the ordering of a few decision-critical trajectories can systematically hijack planning. To exploit this vulnerability, we propose TRAP, a backdoor attack framework for world models that targets imagined trajectory ranking. TRAP combines a tail-aware ranking loss to focus optimization on decision-critical trajectories with dual gating mechanisms that stabilize optimization and regulate when and where the attack penalty is applied. Under trigger conditions, TRAP alters the relative ranking of imagined trajectories to redirect planning outcomes, while largely maintaining the normal ranking structure on clean inputs. Experiments on DreamerV3 and TD-MPC2 across diverse tasks show that TRAP consistently induces sustained behavioral deviations and significant performance degradation, highlighting the need for dedicated security evaluation of world-model-based agents.

Siyuan Duan, Ke Zhang, Xizhao Luo

Department of Computer Science and Technology, Soochow University Suzhou, China

Backdoor Attacks World Model-Based Planning AI Agent Security Model-Based Planning Model-Based RL

May 1, 2026cs.AI

Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially separated routes: 2D video-generative models that emphasize visual future synthesis, 3D scene-centric models that emphasize spatial reconstruction, and JEPA-like latent models that emphasize abstract predictive representations. While each route has made important progress, they still struggle to provide physically reliable, action-controllable, and long-horizon stable predictions for embodied decision making. In this paper, we argue that the bottleneck of world models is no longer only whether they can generate realistic futures, but whether those futures are physically meaningful and useful for action. We propose \emph{Hamiltonian World Models} as a physically grounded perspective on world modeling. The key idea is to encode observations into a structured latent phase space, evolve the latent state through Hamiltonian-inspired dynamics with control, dissipation, and residual terms, decode the predicted trajectory into future observations, and use the resulting rollouts for planning. We discuss how Hamiltonian structure may improve interpretability, data efficiency, and long-horizon stability, while also noting practical challenges in real-world robotic scenes involving friction, contact, non-conservative forces, and deformable objects.

Sen Cui, Jingheng Ma

Tsinghua University

Latent Dynamics Modeling World Models World Model-Based Planning Model-Based Planning Hamiltonian Dynamics Embodied World Models

Apr 28, 2026cs.CV

Lifting Embodied World Models for Planning and Control

World models of embodied agents predict future observations conditioned on an action taken by the agent. For complex embodiments, action spaces are high-dimensional and difficult to specify: for example, precisely controlling a human agent requires specifying the motion of each joint. This makes the world model hard to control and expensive to plan with as search-based methods like CEM scale poorly with action dimensionality. To address this issue, we train a lightweight policy that maps high-level actions to sequences of low-level joint actions. Composing this policy with the frozen world model produces a lifted world model that predicts a sequence of future observations from a single high-level action. We instantiate this framework for a human-like embodiment, defining the high-level action space as a small set of 2D waypoints annotated on the current observation frame, each specifying a near-term goal position for a leaf joint (pelvis, head, hands). Waypoints are low-dimensional, visually interpretable, and easy to specify manually or to search over. We show that the lifted world model substantially outperforms searching directly in low-level joint space (

3.8\times

lower mean joint error to the goal pose), while remaining more compute-efficient and generalizing to environments unseen by the policy.

Alex N. Wang, Trevor Darrell, Pavel Izmailov +2

Computer Science, New York University · BAIR, UC Berkeley

Robotic Control World Model-Based Planning Action-Conditioned World Models Model-Based Planning Embodied World Models

Apr 22, 2026cs.RO

Cortex 2.0: Grounding World Models in Real-World Industrial Deployment

Industrial robotic manipulation demands reliable long-horizon execution across embodiments, tasks, and changing object distributions. While Vision-Language-Action models have demonstrated strong generalization, they remain fundamentally reactive. By optimizing the next action given the current observation without evaluating potential futures, they are brittle to the compounding failure modes of long-horizon tasks. Cortex 2.0 shifts from reactive control to plan-and-act by generating candidate future trajectories in visual latent space, scoring them for expected success and efficiency, then committing only to the highest-scoring candidate. We evaluate Cortex 2.0 on a single-arm and dual-arm manipulation platform across four tasks of increasing complexity: pick and place, item and trash sorting, screw sorting, and shoebox unpacking. Cortex 2.0 consistently outperforms state-of-the-art Vision-Language-Action baselines, achieving the best results across all tasks. The system remains reliable in unstructured environments characterized by heavy clutter, frequent occlusions, and contact-rich manipulation, where reactive policies fail. These results demonstrate that world-model-based planning can operate reliably in complex industrial environments.

Adriana Aida, Walid Amer, Katarina Bankovic +25

Sereact GmbH

Long-Horizon Robotic Manipulation World Models for Robotics Robotics Robotic Manipulation Model-Based Planning Industrial Robotics

Apr 21, 2026cs.LG

Planning in entropy-regularized Markov decision processes and games

We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player games, given a generative model of the environment. SmoothCruiser makes use of the smoothness of the Bellman operator promoted by the regularization to achieve problem-independent sample complexity of order O~(1/epsilon^4) for a desired accuracy epsilon, whereas for non-regularized settings there are no known algorithms with guaranteed polynomial sample complexity in the worst case.

Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Ménard +2

DeepMind Paris · SequeL team, Inria Lille

Value Function Estimation Markov Models Maximum Entropy RL Model-Based Planning Sample-Efficient RL

Apr 20, 2026cs.LG

Scale-free adaptive planning for deterministic dynamics & discounted rewards

We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value function is not known, nor are the rewards bounded. We propose Platypoos, a simple scale-free planning algorithm that adapts to the unknown scale and smoothness of the reward function. We provide a sample complexity analysis for Platypoos that improves upon prior work and holds simultaneously over a broad range of discount factors and reward scales, without the algorithm knowing them. We also establish a matching lower bound showing our analysis is optimal up to constants.

Peter L. Bartlett, Victor Gabillon, Jennifer Healey +1

University of California, Berkeley, USA · Noah’s Ark Lab, Huawei Technologies, London, UK · Adobe Research, San Jose, USA +1

Markov Decision Processes Model-Based Planning Sample-Efficient RL