Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
The long-standing vision of general-purpose robots hinges on their ability to understand and act upon natural language instructions. Vision-Language-Action (VLA) models have made remarkable progress toward this goal, yet their generated actions can still misalign with the given instructions. In this paper, we investigate test-time verification as a means to shrink the "intention-action gap." We first characterize the test-time scaling laws for embodied instruction following and demonstrate that jointly scaling the number of rephrased instructions and generated actions greatly increases test-time sample diversity, often recovering correct actions more efficiently than scaling each dimensio...
| Authors | Jacky Kwok, Xilun Zhang, Mengdi Xu et al. |
|---|---|
| Primary category | cs.RO |
| Published | 12 February 2026 |
| Last updated at source | 18 February 2026 |
Popularity, last 5 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- rl2-vla/cover-vla-fractalModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 22 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.