AI Paper Atlas

Research map / Large language models / Agents, code and math

AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters

Hanjun Luo, Zhimu Huang, Sylvia Chung, Yiran Wang, Yingbin Jin, Jialin Li, Jiang Li, Xinfeng Li, Hanan Salam

ICML 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add memory-augmented agentic judging (AtelierJudge) to a GPT-5.4 judgeGPT-5.4 subjective judge · Subjective verificationSpearman rho vs human experts: 0.55 -> 0.81Improved
add memory-augmented agentic judgingGPT-5.4 subjective judge · Subjective verificationMAE: 0.74 -> 0.33Improved
MLLM prompter writes prompts instead of passing the task text directlyGI-1 (T2I with MLLM middleware), CO tasks · CO objective scoreobjective score (%): 69.6 -> 47.1Hurt
MLLM prompter writes prompts instead of passing the task text directlyFlux Pro (no middleware), CO tasks · CO objective scoreobjective score (%): 32.2 -> 37.5Improved
use Skilled (structured reasoning) prompting strategy instead of Novice for MLLMs (ablation)MLLM prompters, OE tasks · OE tasks, generated image qualitysubjective image scoreNo clear effect
image-based imitation prompting versus text-only constraint planningT0 MLLMs with skilled prompts on GI-1 · IM vs CO objective scoreobjective score (%): 76.1% vs human experts 70.4%Improved
use T2I backend with MLLM middleware (GI-1) in OE tasksT2I backends · OE tasksvariance among promptersImproved
human skilled users prompting on GI-1 CO tasksHuman prompters · CO objective score on GI-1objective score (%): 62.8 -> 81.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy