Metraipolis › archive › dc_fe56058b4165
An Evolutionary Agentic Approach for Open-ended Image Quality Perception — arXiv:2609.22942
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22942
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:59:21.562Z
- SHA-256 of the archived text
982878fc2b395082eea05dfcab0f0fb204d29f621ae035dc6e28f6864cfb147a- Stable URL of this page
https://metraipolis.com/documento/dc_fe56058b4165
How to cite
An Evolutionary Agentic Approach for Open-ended Image Quality Perception — arXiv:2609.22942 — arXiv (en), https://arxiv.org/abs/2609.22942 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe56058b4165 (Metraipolis archive dc_fe56058b4165, sha256 982878fc2b395082eea05dfcab0f0fb204d29f621ae035dc6e28f6864cfb147a)
BibTeX
@misc{dcfe56058b4165,
title = {An Evolutionary Agentic Approach for Open-ended Image Quality Perception — arXiv:2609.22942},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22942},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe56058b4165; sha256 982878fc2b395082eea05dfcab0f0fb204d29f621ae035dc6e28f6864cfb147a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22942. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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-free multi-agent framework that formulates open-ended IQA as explicit protocol construction. Given a target dimension, PACE uses collaborative agents to construct an evaluation protocol composed of verifiable Visual Question Answering (VQA) probes, grounding evaluation in concrete visual evidence rather than holistic impressions. The resulting protocol is calibrated using only four human-annotated images per dimension, while a dual-track scoring mechanism aligns model perception with human scoring scales. Across traditional IQA, structural fidelity, context-aware aesthetics, and newly defined open-ended dimensions, PACE consistently improves its MLLM backbone, achieving competitive performance across diverse IQA settings, and reduces the Holistic Override Rate (HOR) from 44.4\% to 8.6\%. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.22942 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T21:45:20.831Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).