# CoRL 2026 paper proposes language feedback policy that can steer frozen VLAs harmlessly

- Source: arXiv cs.RO
- Published: 2026-10-19T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/qc8qk2l8l1074paefngrehjut
- Original: https://arxiv.org/abs/2606.12299

## Summary

The paper proposes a framework that interactively searches for language sequences that improve closed-loop VLA task performance, distills them into a test-time language feedback policy (LFP), and trains an improvement head to predict when language steering will be effective, then applies conformal calibration to the improvement head to prevent harmful interventions.