RISE: Adaptive Imagination for World Action Models

2026-08-19

AI Summary

为解决固定想象预算问题，提出RISE框架通过自适应选择性展开来优化世界行动模型的规划性能。

Abstract

World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagination budget to every scene. We propose RISE (\textbf{R}efining \textbf{I}magination through \textbf{SE}lective Rollout), a system-level adaptive imagination framework that makes sequential \textsc{Roll}/\textsc{Stop} decisions according to the expected planning benefit of continued rollout. At each step, a Latent Evaluator estimates the risk revealed by the current prefix and how much planning could improve if imagination continues, while a Rollout Gate weighs this expected benefit against additional computation cost. Since factual driving logs expose only one realized future, we further construct \textbf{CounterDrive}, a counterfactual dataset with diverse outcomes and risk levels, to enrich future dynamics and provide localized risk supervision. Each retained sample undergoes expert verification and annotation of trajectory validity, incident onset, and causal category, providing a reusable resource for safety-critical world-modeling research. Experiments on NAVSIM and nuScenes show that RISE achieves the best overall planning performance while reducing unnecessary rollout, with additional transfer results supporting its plug-in generality across WAM architectures.

Problem

• World Action Models
• imagination budget
• adaptive imagination
• planning benefit
• computation cost

Innovation

• Adaptive Imagination
• World Action Models
• Selective Rollout
• Latent Evaluator
• Counterfactual Dataset