Execution Logs Sway VLM Judges of Robot Progress
Overview & Synopsis
Vision-language models now grade robot videos, and text placed beside the frames can change their verdicts. On clips where the robot is losing progress, we add one log line saying the robot is making progress. Across Gemini, Qwen and GPT judges, this flips correct verdicts to progress 10 to 35 percentage points more often than a neutral line does. A one-line warning that the log may be wrong removes most of this effect. Selected fake "task complete" claims flip half of Qwen's correct verdicts, against a tenth for unrelated log lines. They have no detectable effect on Gemini.
Indexed from repository: arXiv
(
arxiv.org)
Keyboard Shortcuts:
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Execution Logs Sway VLM Judges of Robot Progress |
|---|---|
| Author / Organization | Weiyan Zhao, Sunny Yang |
| Subject & Discipline | cs.LG |
| Categories | Computer Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-8999 |
| Original Source Link | Visit Source Page on arxiv.org » |