Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model

TL;DR

This paper introduces Action-Draft-and-Verify (ADV), a framework combining diffusion and auto-regressive methods for vision-language-action models, improving robustness and success rates in embodied tasks.

Contribution

The paper proposes a novel self-verifying framework that drafts multiple action candidates and selects the best using a VLM, enhancing performance over diffusion-only baselines.

Findings

+4.3 points success rate in simulation

+19.7 points success rate in real-world

Single-pass VLM reranking with improved robustness

Abstract

Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while auto-regressive generation can be slower and less accurate at low-level control. Yet auto-regressive paradigms still provide complementary priors that can improve robustness and generalization in out-of-distribution environments. To leverage both paradigms, we propose Action-Draft-and-Verify (ADV): diffusion action expert drafts multiple candidate action chunks, and the VLM selects one by scoring all candidates in a single forward pass with a perplexity-style metric. Under matched backbones, training data, and action-chunk length, ADV improves success rate by +4.3 points in simulation and +19.7 points in real-world over diffusion-based baseline, with a single-pass VLM reranking overhead.