AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910246497157120 |
|---|---|
| author | Luo, Hanjun Huang, Zhimu Chung, Sylvia Wang, Yiran Jin, Yingbin Li, Jialin Li, Jiang Li, Xinfeng Salam, Hanan |
| author_facet | Luo, Hanjun Huang, Zhimu Chung, Sylvia Wang, Yiran Jin, Yingbin Li, Jialin Li, Jiang Li, Xinfeng Salam, Hanan |
| contents | Text-to-image (T2I) systems increasingly rely on upstream prompters, either humans or multimodal large language models (MLLMs), to translate user intent into detailed prompts. Yet current benchmarks fix the prompt and only evaluate T2I models, leaving the prompting proficiency of this upstream component entirely unmeasured. We introduce AtelierEval, the first unified benchmark that quantifies prompting proficiency across 360 expert-crafted tasks. Grounded in a cognitive view, it spans three task categories and instantiates tasks using a taxonomy of real-world challenges, with a dual interface for both humans and MLLMs. To enable scalable and reliable evaluation, we propose AtelierJudge, a skill-based, memory-augmented agentic evaluator. It produces subjective and objective scores for prompt-image pairs, achieving a Spearman correlation of 0.79 with human experts, approaching human performance. Extensive experiments benchmark 8 MLLMs against 48 human users across 4 T2I backends, validate AtelierEval as a robust diagnostic tool, and reveal the superiority of mimicry over planning, advocating for an image-augmented direction for future prompters. Our work is released to support future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22645 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters Luo, Hanjun Huang, Zhimu Chung, Sylvia Wang, Yiran Jin, Yingbin Li, Jialin Li, Jiang Li, Xinfeng Salam, Hanan Artificial Intelligence Text-to-image (T2I) systems increasingly rely on upstream prompters, either humans or multimodal large language models (MLLMs), to translate user intent into detailed prompts. Yet current benchmarks fix the prompt and only evaluate T2I models, leaving the prompting proficiency of this upstream component entirely unmeasured. We introduce AtelierEval, the first unified benchmark that quantifies prompting proficiency across 360 expert-crafted tasks. Grounded in a cognitive view, it spans three task categories and instantiates tasks using a taxonomy of real-world challenges, with a dual interface for both humans and MLLMs. To enable scalable and reliable evaluation, we propose AtelierJudge, a skill-based, memory-augmented agentic evaluator. It produces subjective and objective scores for prompt-image pairs, achieving a Spearman correlation of 0.79 with human experts, approaching human performance. Extensive experiments benchmark 8 MLLMs against 48 human users across 4 T2I backends, validate AtelierEval as a robust diagnostic tool, and reveal the superiority of mimicry over planning, advocating for an image-augmented direction for future prompters. Our work is released to support future research. |
| title | AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.22645 |