Aryo Pradipta Gema

This work finds that the wording of the question affects VLMs in two opposite ways: verbose paraphrasing reduces drift variance by 70--81% on the 8B models and the practical recipe---pad the prompt---further yields measurable gains in accuracy, even under image corruption.

Models show a striking 40% drop in verbalized commitment when cues come from tool returns instead of user messages, challenging assumptions about reasoning trace reliability.

Forget curated prompts: SCOPE's self-play framework co-evolves task generation and solving, outperforming models trained on thousands of human-written prompts.