arXiv:2606. 14418v1 Announce Type: new Abstract: We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space.
arXiv:2601. 00969v3 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models provide strong action priors for robotic manipulation, but their reactive behavior can fail under distribution shift and long-horizon task structure.
arXiv:2608. 12078v1 Announce Type: cross Abstract: Learning world models from offline trajectories enables agents to accomplish different tasks through planning.
Reinforced Planning with Latent World Models (RP1) is a novel method that learns to evaluate imagined outcomes via a critic and to improve multi‑step plans through an optimizer trained offline on world‑model roll‑outs. It is the first approach to fully learn plan improvement and can be attached to any pretrained latent world model. In experiments on visual navigation, arm reaching, and robotic manipulation, RP1 outperforms hand‑designed search algorithms, achieving near‑perfect success while using far fewer roll‑outs and running up to 67× faster than the strongest alternative.
DeepJEPA is a weight‑tied joint‑embedding predictive world model that treats transition depth as an inner test‑time scaling axis, learning when additional recurrent updates are worthwhile for each candidate and rollout step. Unlike traditional planners that uniformly deepen every transition, DeepJEPA concentrates extra computation on decision‑critical events such as contact onset and sustained object interaction, achieving comparable or better performance with only 1.00–1.26 updates per transition across five visual‑control settings. The approach demonstrates that improved planning does not require uniformly better object‑state decodability, but rather targeted internal computation where it can alter the planner’s elite set and action selection.
Reinforced Planning with Latent World Models introduces RP1, a neural planner that learns to evaluate imagined outcomes via a critic and improve multi‑step plans through an optimizer trained offline on world‑model roll‑outs. Unlike existing planners that are hand‑designed or only inform policies, RP1 fully learns to refine plans and can be attached to any pretrained latent world model. In experiments on visual navigation, arm reaching, and robotic manipulation, RP1 outperforms hand‑designed search algorithms, achieving near‑perfect success while using 1,000× fewer roll‑outs and up to 67× faster inference.
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.
arXiv:2606. 15197v1 Announce Type: cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments.
arXiv:2608. 14125v1 Announce Type: new Abstract: LeWM is a lightweight visual world model that learns latent dynamics end-to-end from pixels and ranks candidate action sequences by the distance between their predicted endpoints and the goal.
arXiv:2606. 26217v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs), including recent LeWorldModel (LeWM), have become a promising foundation for reconstruction-free visual world models.
arXiv:2609.39235v1 Announce Type: cross Abstract: World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet exis...
Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance.