# 面向测试时验证 VLA 策略的流支持加权候选提案

> 原文链接：https://robotics.hellobike.com/papers/2026-10-10-2610-14588
> 频道：papers | 更新日期：2026-10-10 | 标签：arxiv, cs.RO
> 核心摘要：针对VLA测试时采样候选冗余的proposal contraction，提出ADS以流支持加权校正训练，并在仿真和四个实体机器人任务验证。

# 面向测试时验证 VLA 策略的流支持加权候选提案

::: v-pre
> 原文链接：[Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies](https://arxiv.org/abs/2610.14588)（arXiv 2610.14588 · 发布日期：2026-10-10）

**Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies**

针对VLA测试时采样候选冗余的proposal contraction，提出ADS以流支持加权校正训练，并在仿真和四个实体机器人任务验证。

## 核心要点

- 下游微调会造成proposal contraction，候选随预算增长仍高度冗余。
- ADS在训练中采样K条额外轨迹，用流支持得分加权校正动作分布。
- RoboCasa成功率由57.6%升至63.0%，固定验证器提升2.4至4.9点。
- 真机操作中TokenPB最高提升13.0点；训练成本上升，部署成本不变。

**验证范围与局限**：验证范围为仿真和四个实体机器人任务。

## 英文摘要 (Abstract)

Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fine-tuning works against that promise. A vision-language-action model trained to solve one task distribution concentrates its flow-matching decoder around the dominant demonstrated action, so repeated samples differ only marginally and the verifier receives many copies of one decision. We call this proposal contraction and identify it as a key constraint on test-time scaling: repeated samples can remain highly redundant as the candidate budget grows. Action Dynamic Sampling (ADS) alleviates the constraint on the proposal side, during training. At each training step, ADS integrates $K$ additional trajectories from the current policy under fresh base noise, scores each by the flow support along its path with a Hutchinson trace estimator, and corrects the policy's local action distribution toward this weighted set through a detached finite-set KL term. Training cost rises; deployment cost is unchanged. Across simulation and four physical-robot tasks, ADS raises proposal spread without the success penalty that Gaussian perturbation incurs, lifts oracle best-of-8 success on RoboCasa from 57.6% to 63.0%, improves fixed verifiers by 2.4 to 4.9 points in simulation, and raises TokenPB by up to 13.0 points on real-world manipulation.

作者：Chen Zhao, Zipeng Ye, Haitao Shen, Guanlin Li, Yuchen Xie, Jing Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.14588：Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies](https://arxiv.org/abs/2610.14588)