# Execution logs sway VLM judgments of robot progress

- Source: arXiv cs.RO
- Published: 2026-10-27T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/bm24rpg31kyfo2043mufcrrid
- Original: https://arxiv.org/abs/2610.34151

## Summary

The study tested how text placed beside frames affects vision-language models judging robot videos: when a line saying "making progress" was added to clips where the robot was falling behind, Gemini, Qwen, and GPT judges flipped correct verdicts to "progress" 10 to 35 percentage points more often than with neutral text.