The paper proposes that reusable agent skills should incorporate visual elements alongside text, introduces three forms of visual skills and an automatic conversion system, and reports better performance on GUI and visual-centric tasks.
Mayer and Roxana Moreno
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Randomized trial finds diverse LLM explanations improve open-ended accuracy by 7.7% over generic ones in introductory programming without raising cognitive load.
citing papers explorer
-
Exploring the Value of Diverse LLM Explanations in Introductory Programming
Randomized trial finds diverse LLM explanations improve open-ended accuracy by 7.7% over generic ones in introductory programming without raising cognitive load.