Metraipolis › archive › dc_d2f2fd5c408a
PainterBench: A Figural Divergent-Thinking Benchmark for Tool-Using Language Models — arXiv:2609.34195
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34195
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:57:31.371Z
- SHA-256 of the archived text
70c85f83c8900f2fdaa1f998c9f97f325d32279577a82064b4f3cc220fd426db- Stable URL of this page
https://metraipolis.com/documento/dc_d2f2fd5c408a
How to cite
PainterBench: A Figural Divergent-Thinking Benchmark for Tool-Using Language Models — arXiv:2609.34195 — arXiv (en), https://arxiv.org/abs/2609.34195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2f2fd5c408a (Metraipolis archive dc_d2f2fd5c408a, sha256 70c85f83c8900f2fdaa1f998c9f97f325d32279577a82064b4f3cc220fd426db)
BibTeX
@misc{dcd2f2fd5c408a,
title = {PainterBench: A Figural Divergent-Thinking Benchmark for Tool-Using Language Models — arXiv:2609.34195},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34195},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2f2fd5c408a; sha256 70c85f83c8900f2fdaa1f998c9f97f325d32279577a82064b4f3cc220fd426db},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Figural divergent thinking is the ability to develop a given shape fragment into an original drawing. In humans, this ability is assessed with incomplete-drawing tasks. We introduce PainterBench, a benchmark that ports the incomplete-drawing task to the agentic setting. The agent draws on a canvas through tool calls and observes the result after every turn. The canvas includes a starting shape which cannot be erased, and the agent's goal is to incorporate this shape into the most original drawing it can produce. The task is open-ended, and the agent itself decides when the drawing is finished. The benchmark tests incremental visual planning over a short horizon and the transfer of creative ability from pretraining to multi-turn tool use. We evaluate 14 multimodal language models from small to frontier scale. Across the primary study and six sensitivity analyses, we collect 2,700 drawings and crowdsource creativity and recognizability ratings for every drawing and for 300 human reference drawings. We also present ViDrA-adapted, an automated scorer that predicts human creativity ratings of agent drawings (r = 0.85 on random held-out test split). Figural divergent thinking varies widely across the 14 models, and GPT-6 Astra produces the most creative drawings. Relative to the human drawings, the agent drawings score higher in creativity but lower in recognizability. We release the final drawings, per-round canvas snapshots, tool call traces, stimulus bank, benchmark harness, crowdsourced ratings (N = 72,000), and ViDrA checkpoint. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.34195 — 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 2026-10-07T20:29:01.475Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).