arXiv:2609.00455v1 Announce Type: new Abstract: Large language models (LLMs) are being used as policies for autonomous decision-making and planning in many domains. Despite their strong reasoning cap...
arXiv:2604. 25416v2 Announce Type: replace Abstract: Model-based reinforcement learning distinguishes between dynamics models operating on proprioceptive states and latent dynamics models typically operating on high-dimensional image observations.
The paper introduces Dual-Frontier, a learning principle that determines when an agent should trust its world model for decision-making. It formalizes the failure-attribution problem as a counterfactual decomposition of return loss and shows that its components cannot be identified from passive interaction, even for finite-horizon planners. Dual-Frontier allows a model‑guided decision only when the predicted advantage exceeds a certified bound on decision‑relevant world‑model error; otherwise, the agent focuses on verifying the model. The authors provide theoretical guarantees, adaptive evidence reuse, and experimental validation on controlled and realistic benchmarks, demonstrating improved decision quality and reliability.
arXiv:2606. 31422v2 Announce Type: replace Abstract: Language agents acting over long horizons must maintain beliefs about tool states, object locations, graph edges, and subgoal dependencies.
The paper introduces Imagine-then-Plan (ITP), a framework that lets agents learn by interacting with a learned world model to generate multi-step imagined trajectories. ITP features an adaptive lookahead mechanism that balances ultimate goals with task progress, producing richer signals about future outcomes. Experiments on various benchmarks show that ITP outperforms existing baselines, and analyses suggest the adaptive lookahead improves reasoning for complex tasks.
arXiv:2609.05834v1 Announce Type: new Abstract: World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the...
arXiv:2606. 30639v1 Announce Type: new Abstract: World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution.
arXiv:2507. 06722v2 Announce Type: replace-cross Abstract: Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations.
arXiv:2607. 07196v1 Announce Type: cross Abstract: Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world, and returning a success or safety verdict.
arXiv:2608.20430v1 Announce Type: new Abstract: World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagi...
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...
arXiv:2606. 01626v1 Announce Type: new Abstract: Planning with a learned latent world model is a promising route to control from raw pixels, but a strong world model alone is not enough.