SOURCE-LINKED INTELLIGENCE

An Evolutionary Agentic Approach for Open-ended Image Quality Perception

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plausibility and text-rendering correctness. However, existing IQA models rely on fixed definitions and heavy supervision, making them difficult to extend to open-ended perceptual dimensions. We identify holistic bias as an important limitation: when scoring an unseen dimension, models reuse generic quality priors, leading to scoring errors and rank inversion. To address this, we propose PACE (Perceptual Agentic Collaborative Evolution), a training-

Read original source ↗ Open in workspace

recordType

paper

region

Global