Metraipolis › archive › dc_ee9e24bf048c

ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding — arXiv:2609.13240

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13240
License (as archived)
CC0-1.0
Archived
2026-10-16T01:52:32.073Z
SHA-256 of the archived text
8ff542c1c2868cd7bd245ae429b54c59bd7a5cd16284985ba14683ab94b1858b
Stable URL of this page
https://metraipolis.com/documento/dc_ee9e24bf048c

How to cite

ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding — arXiv:2609.13240 — arXiv (en), https://arxiv.org/abs/2609.13240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee9e24bf048c (Metraipolis archive dc_ee9e24bf048c, sha256 8ff542c1c2868cd7bd245ae429b54c59bd7a5cd16284985ba14683ab94b1858b)
BibTeX
@misc{dcee9e24bf048c,
  title = {ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding — arXiv:2609.13240},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee9e24bf048c; sha256 8ff542c1c2868cd7bd245ae429b54c59bd7a5cd16284985ba14683ab94b1858b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The AffectiveArt Multidimensional Art Emotion Understanding task asks to jointly predict an artwork's fine-grained emotion (12 classes, 1549:1 head-to-tail ratio), binary valence/arousal, and five attribute-grounded descriptions -- sub-tasks that exhibit strong empirical trade-offs, so the single-model solutions we tried do not jointly optimize all of them well. We present ArtSociety, a multi-agent framework that assembles heterogeneous multimodal experts -- a DINOv2-Giant vision agent (A1), a scene-grounded CoT fine-tuned MLLM (A2), and three closed-source reasoning agents (A3-A5) -- and coordinates them with two training-free controllers: (i) a rare-class-aware voting arbiter that lowers the agreement threshold for tail emotions, exploiting decorrelated error patterns across agent families; and (ii) a description-first reasoning agent whose DESCRIBE-then-CLASSIFY chain of thought forces visual evidence before label commitment, yielding near-perfect grounded descriptions. A task-routing policy directs the hard emotion task to the full five-agent ensemble while assigning the near-saturated valence/arousal and generative description tasks to the single strongest reasoning agent. On the official test set (1,000 artworks), ArtSociety achieves an Overall Score of 0.8870 (Classification 0.7789, Description 0.9952). An eleven-variant ablation study reveals that, once method and scale saturate at around 0.76, the decisive gains come from agent collaboration and data-side supervision -- a 30B MoE model trained on older data does not outperform an 8B model trained on better data. Code is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.13240 — 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 2026-10-16T01:25:23.469Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).