# RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

arXiv: https://arxiv.org/abs/2510.10975 · HTML: https://mlsanity.com/paper/2510.10975/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Vision-language-action models / [Failure recovery and robustness](https://mlsanity.com/vla/failure-recovery-and-robustness/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling](https://mlsanity.com/paper/2502.06703/) (2025)
- [RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete](https://mlsanity.com/paper/2502.21257/) (2025)
- [Unified Vision-Language-Action Model](https://mlsanity.com/paper/2506.19850/) (2025)
- [OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning](https://mlsanity.com/paper/2505.11917/) (2025)
- [OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation](https://mlsanity.com/paper/2505.03912/) (2025)
- [HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers](https://mlsanity.com/paper/2410.05273/) (2024)
- [Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy](https://mlsanity.com/paper/2503.19757/) (2025)
- [Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation](https://mlsanity.com/paper/2410.08001/) (2024)
- [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2506.17811/) (2025)
- [Hume: Introducing System-2 Thinking in Visual-Language-Action Model](https://mlsanity.com/paper/2505.21432/) (2025)
- [Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning](https://mlsanity.com/paper/2412.12953/) (2024)
- [Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning](https://mlsanity.com/paper/2412.11974/) (2024)
- [From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control](https://mlsanity.com/paper/2405.04798/) (2024)

## Built on by (most cited first, 19 of 19)

- [CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2601.02295/) (2026)
- [Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models](https://mlsanity.com/paper/2605.07514/) (2026)
- [Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion](https://mlsanity.com/paper/2511.14178/) (2025)
- [Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation](https://mlsanity.com/paper/2607.17454/) (2026)
- [IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2602.20715/) (2026)
- [Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs](https://mlsanity.com/paper/2605.10094/) (2026)
- [TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation](https://mlsanity.com/paper/2605.25547/) (2026)
- [τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation](https://mlsanity.com/paper/2608.16885/) (2026)
- [VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2606.10568/) (2026)
- [A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference](https://mlsanity.com/paper/2609.01679/) (2026)
- [ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models](https://mlsanity.com/paper/2608.13438/) (2026)
- [E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation](https://mlsanity.com/paper/2606.27268/) (2026)
- [Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning](https://mlsanity.com/paper/2606.08231/) (2026)
- [FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy](https://mlsanity.com/paper/2608.16697/) (2026)
- [Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal Policies](https://mlsanity.com/paper/2608.17484/) (2026)
- [No Free Checker: A Survey of Verifiers for Robot Policies](https://mlsanity.com/paper/2609.09250/) (2026)
- [ARS: Agentic Reward System for Robot Learning](https://mlsanity.com/paper/2609.34484/) (2026)
- [DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling](https://mlsanity.com/paper/2610.04933/) (2026)
- [Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies](https://mlsanity.com/paper/2610.14588/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have become a prominent paradigm for embodied intelligence, yet further performance improvements typically rely on scaling up training data and model size -- an approach that is prohibitively expensive for robotics and fundamentally limited by data collection costs. We address this limitation with RoVer, an embodied test-time scaling framework that uses a Robot Process Reward Model (PRM) as a Test-Time Verifier to enhance the capabilities of existing VLA models without modifying their architectures or weights. Specifically, RoVer (i) assigns scalar-based process rewards to evaluate the reliability of candidate actions, and (ii) predicts an action-space direction for candidate expansion/refinement. During inference, RoVer generates multiple candidate actions concurrently from the base policy, expands them along PRM-predicted directions, and then scores all candidates with PRM to select the optimal action for execution. Notably, by caching shared perception features, it can amortize perception cost and evaluate more candidates under the same test-time computational budget. Essentially, our approach effectively transforms available computing resources into better action decision-making, realizing the benefits of test-time scaling without extra training overhead. Our contributions are threefold: (1) a general, plug-and-play test-time scaling framework for VLAs; (2) a PRM that jointly provides scalar process rewards and an action-space direction to guide exploration; and (3) an efficient direction-guided sampling strategy that leverages a shared perception cache to enable scalable candidate generation and selection during inference.