Beyond Visual Quality: A Study of Test-Time Planning with World Action Models

arXiv:2609.24745 · cs.RO · Submitted 2026-09-21 · Read on arXiv

cs.RO

Submitted: 2026-09-21

Updated: 2026-09-21

Terminology

• Alignment — 18× in this paper · explained in 1 episode
• Consistency — 16× in this paper · explained in 3 episodes
• World Model — 13× in this paper · explained in 7 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• AUC — 9× in this paper · explained in 2 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Steering — 4× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Latent Dynamics — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Latent World Models — 1× in this paper · explained in 2 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• Inference-time Physics Alignment of Video Generative Models with Latent World Models
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
• RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation
• RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
• From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
• Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
• Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
• Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation
• ACID: Action Consistency via Inverse Dynamics for Planning with World Models
• $\tau_0$-WM: A Unified Video-Action World Model for Robotic Manipulation
• Qwen3-VL Technical Report
• RynnVLA-002: A Unified Vision-Language-Action and World Model
• World Action Models are Zero-shot Policies
• WorldVLA: Towards Autoregressive Action World Model
• Causal World Modeling for Robot Control
• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
• DynamicWAM: Dual-Path Motion Conditioning for World-Action Models in Dynamic Manipulation
• SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving