Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction

• URL: http://arxiv.org/abs/2608.07420v1
• Date: Fri, 07 Aug 2026 17:05:44 GMT
• Title: Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
• Abstract summary: We argue that long-horizon accuracy is better achieved by optimizing directly, through an end-to-end endpoint prediction objective.<n>We introduce the Direct Prediction World Model (DPWM), a non-recursive architecture that compresses an action sequence into a single embedding and predicts the endpoint observation in a single forward pass.
• Score: 14.604042842855002
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions. This creates a fundamental mismatch: few-step losses optimize local transition fidelity, while long-horizon prediction depends on how errors and gradients propagate through the entire trajectory. As a result, transitions with different downstream influence on the endpoint are treated uniformly during training, and small local errors are amplified through recursive inference. We argue that long-horizon accuracy is better achieved by optimizing directly, through an end-to-end endpoint prediction objective. To instantiate this paradigm, we introduce the Direct Prediction World Model (DPWM), a non-recursive architecture that compresses an action sequence of arbitrary length into a single embedding and predicts the endpoint observation in a single forward pass. This design avoids recurrent rollout in both prediction and gradient propagation, making long-horizon end-to-end training practical at horizons where unrolled autoregressive training becomes unstable. Empirically, DPWM substantially improves long-horizon endpoint prediction over recursive world-model baselines on continuous-control and pixel-based benchmarks, with larger gains as the prediction horizon increases. We further show that recurrent baselines benefit similarly when retrained with the same long-horizon endpoint objective, supporting our central claim that the training objective, rather than the particular backbone choice, is the main driver of long-horizon prediction accuracy. Our results suggest that world models can benefit from being trained and evaluated at the temporal scales where they are ultimately used, shifting the focus from local transition modeling toward long-horizon predictive accuracy.

Related papers

• Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning [40.09669638091686]
  We propose a framework that learns to predict future latent states conditioned on action sequences of variable lengths.<n>Experiments show that Variable-length Latent World Models significantly improve latent space world models.
  arXiv  Detail & Related papers  (2026-06-19T21:50:15Z)
• From Short Histories to Long Futures: Horizon-Aware Graph Neural Networks for Long Horizon Forecasting [1.6114012813668932]
  Deep neural network can serve as efficient emulators, but most are trained only for next-step prediction.<n>We propose a multi-horizon graph neural network emulator that learns state-to-state transitions from a single current time to multiple future lead times.<n> Experiments on multi-decadal Pine Island Glacier simulations show that our approach achieves higher long-range accuracy and improved stability.
  arXiv  Detail & Related papers  (2026-05-28T13:58:48Z)
• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• Towards Scaling Law Analysis For Spatiotemporal Weather Data [50.25336689856158]
  We extend neural scaling analysis for autoregressive weather forecasting from single-step training loss to long rollouts and per-channel metrics.<n>We find strong cross-channel and cross-horizon heterogeneity: pooled scaling can look favorable while many channels degrade at late leads.<n>We discuss implications for weighted objectives, horizon-aware curricula, and resource allocation across outputs.
  arXiv  Detail & Related papers  (2026-04-06T18:14:53Z)
• TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Driving [10.160418242076284]
  Trajectory prediction is essential for autonomous driving, enabling vehicles to anticipate the motion of surrounding agents.<n>We propose TaPD, a unified plug-and-play framework for observation-adaptive trajectory forecasting under variable history lengths.<n>Experiments on Argoverse 1 and Argoverse 2 show that TaPD consistently outperforms strong baselines across all observation lengths.
  arXiv  Detail & Related papers  (2026-03-06T12:51:32Z)
• SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction [3.870589001283509]
  We propose a semantic-key-point-conditioned trajectory modeling framework.<n>It decomposes long-horizon prediction into global semantic decision-making and local motion modeling.<n>Experiments on real-world AIS data demonstrate that the proposed method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-01-26T14:42:31Z)
• Adaptive Conformal Prediction Intervals Over Trajectory Ensembles [50.31074512684758]
  Future trajectories play an important role across domains such as autonomous driving, hurricane forecasting, and epidemic modeling.<n>We propose a unified framework based on conformal prediction that transforms sampled trajectories into calibrated prediction intervals with theoretical coverage guarantees.
  arXiv  Detail & Related papers  (2025-08-18T21:14:07Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting [54.273455592965355]
  Uncertainty in future trajectories stems from two sources: (a) sources known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works.
  arXiv  Detail & Related papers  (2020-12-02T21:01:29Z)
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors [124.30562402952319]
  The ability to predict and plan into the future is fundamental for agents acting in the world. Current learning approaches for visual prediction and planning fail on long-horizon tasks. We propose a framework for visual prediction and planning that is able to overcome both of these limitations.
  arXiv  Detail & Related papers  (2020-06-23T17:58:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.