arXivHanjun Luo, Zhimu Huang, Sylvia Chung, Yiran Wang, Yingbin Jin, Jialin Li, Jiang Li, Xinfeng Li, Hanan SalamThu, May 21, 2026, 8:51 AM PDT
score 14.8
New benchmark measures how well humans and AI write image prompts
Original: AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
Source: arxiv.org ↗
Writing ELI5 summary…