# Harness VLA open-sourced, achieves 82.4% on LIBERO-Pro

- Source: 正行创新 · X
- Published: 2026-07-22T03:49:39.000Z
- RoboHot: https://robohot.news/en/items/m7ef5r6oc2xz18xuiiimsjqj9
- Original: https://x.com/StridingAI/status/2079775859494556037

## Summary

@ChaoYuTHU has open-sourced Harness VLA, which adds a Harness Layer to organize VLA models without modifying their weights. On LIBERO-Pro, Harness VLA scores 82.4%, compared with Pi_RLinf at 50%, Berkeley RATS at 43.8%, and NVIDIA Cap-X at 18.2%. Striding AI posted this tweet and sees it as a possible sign of a shift from end-to-end VLA to Harness VLA.

## Why it matters

The tweet provides comparison numbers with other VLA approaches on the same benchmark, letting readers judge how much headroom a plug-in structure that does not change weights offers.