# Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts arXiv: https://arxiv.org/abs/2605.22446 · HTML: https://mlsanity.com/paper/2605.22446/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Embodied and robot world models, one of 11 directions in World models. - Builds on 35 of its 39 references that are in the map. - First posted on arXiv 21 May 2026. ## Placed in - World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/) - Vision-language-action models / [VLA architectures and generalization](https://mlsanity.com/vla/vla-architectures-and-generalization/) ## Builds on (most cited first, 30 of 35) - [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017) - [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024) - [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025) - [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023) - [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025) - [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024) - [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024) - [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019) - [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025) - [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024) - [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018) - [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025) - [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024) - [Conservative Safety Critics for Exploration](https://mlsanity.com/paper/2010.14497/) (2020) - [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025) - [RynnVLA-002: A Unified Vision-Language-Action and World Model](https://mlsanity.com/paper/2511.17502/) (2025) - [WMPO: World Model-based Policy Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2511.09515/) (2025) - [WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios](https://mlsanity.com/paper/2510.26125/) (2025) - [RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation](https://mlsanity.com/paper/2509.15965/) (2025) - [WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL](https://mlsanity.com/paper/2602.13977/) (2026) - [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025) - [Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations](https://mlsanity.com/paper/2108.01846/) (2021) - [World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy](https://mlsanity.com/paper/2602.06508/) (2026) - [Multi-agent Embodied AI: Advances and Future Directions](https://mlsanity.com/paper/2505.05108/) (2025) - [World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/2509.19080/) (2025) - [Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering](https://mlsanity.com/paper/2411.11504/) (2024) - [RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic](https://mlsanity.com/paper/2512.21220/) (2025) - [NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models](https://mlsanity.com/paper/2605.07794/) (2026) ## Built on by (most cited first, 5 of 5) - [CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation](https://mlsanity.com/paper/2607.26789/) (2026) - [AEGIS: A Backup Reflex for Physical AI](https://mlsanity.com/paper/2606.06660/) (2026) - [TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views](https://mlsanity.com/paper/2607.21910/) (2026) - [IMPLY: Physically Anchored Consistency for World-Model Rollouts](https://mlsanity.com/paper/2609.12441/) (2026) - [Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies](https://mlsanity.com/paper/2610.14588/) (2026) ## Abstract (arXiv) While large vision-language-action (VLA) models and generative world models (WM) have advanced long-horizon embodied intelligence, their practical deployment remains challenged by uncertainty in learning-based action generation. Low-quality actions may cause physical failures during execution or lead to misleading world-model rollouts with redundant rendering costs. To address this issue, we propose Pre-VLA, a unified runtime verification architecture that performs preemptive action validity assessment before physical execution or world-model imagination. Pre-VLA leverages an efficient multimodal backbone with modality-aware pooling and a lightweight dual-branch head to predict both safety confidence and critic-derived advantage scores for candidate action chunks. To handle severe class imbalance and unstable boundary decisions, we train Pre-VLA with a multi-task objective combining Focal classification, advantage regression, and soft-threshold calibration. During deployment, a dual-mode preemptive resampling scheduler filters low-quality actions and triggers adaptive resampling under a limited computation budget. Experiments on the LIBERO benchmark show that Pre-VLA improves the average closed-loop success rate across four suites from 30.79% to 37.62% over RynnVLA-002, reduces task execution steps, achieves 183.9 ms average forward verification time per action chunk, and mitigates error accumulation in world-model rollouts.