paper-with-me

홈 › Papers

RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models

2025-06-21 · Jacky Kwok, Christopher Agia, Rohan Sinha, Matt Foutter, Shulu Li, Ion Stoica, Azalia Mirhoseini, Marco Pavone

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in visuomotor control, yet ensuring their robustness in unstructured real-world environments remains a persistent challenge. In this paper, we investigate test-time scaling through the lens of sampling and verification as means to enhance the robustness and generalization of VLAs. We first demonstrate that the relationship between action error and the number of generated samples follows an exponentiated power law across a range of VLAs, indicating the existence of inference-time scaling laws. Building on these insights, we introduce RoboMonkey, a test-time scaling framework for VLAs. At deployment, RoboMonkey samples a small set of actions from a VLA, applies Gaussian perturbation and majority voting to construct an action proposal distribution, and then uses a Vision Language Model (VLM)-based verifier to select the optimal action. We propose a synthetic data generation pipeline for training such VLM-based action verifiers, and demonstrate that scaling the synthetic dataset consistently improves verification and downstream accuracy. Through extensive simulated and hardware experiments, we show that pairing existing VLAs with RoboMonkey yields significant performance gains, achieving a 25% absolute improvement on out-of-distribution tasks and 8% on in-distribution tasks. Additionally, when adapting to new robot setups, we show that fine-tuning both VLAs and action verifiers yields a 7% performance increase compared to fine-tuning VLAs alone.

📄 PDF Abstract BibTeX arXiv:2506.17811

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data GenerationVision-Language-Action

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification

2025-02-03 · Eric Zhao, Pranjal Awasthi, Sreenivas Gollapudi

Sampling-based search, a simple paradigm for utilizing test-time compute, involves generating multiple candidate responses and selecting the best one -- typically by verifying each response for correctness. In this paper…

Attribute

SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling

2025-01-31 · Jiefeng Chen, Jie Ren, Xinyun Chen, Chengrun Yang 외

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, conventional approaches such as repeated …

Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers

2025-02-27 · Shalev Lifshitz, Sheila A. McIlraith, Yilun Du

By utilizing more computational resources at test-time, large language models (LLMs) can improve without additional training. One common strategy uses verifiers to evaluate candidate outputs. In this work, we propose a n…

$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

2026-03-04 · Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran 외 arxiv

Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. How…

Code Generation

BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies

2026-05-28 · Anya Singh, Cabrel Happi, Jai Relan, Varun Nair 외 arxiv

Test-time scaling for vision-language-action (VLA) policies, methods such as RoboMonkey, SEAL, MG-Select, and V-GPS, samples K candidate action chunks at inference and executes the verifier-best. When all K candidates ar…