creative software developers

Abstract: Vision-language models (VLMs) are deployed as zero-shot judges of image aesthetics, and panels of several models are recommended, on thin evidence, as the way to make such judges reliable. On two human-rated datasets, EVA and PARA, we find that a panel of holistic judges never significantly beats its best member, whether the verdicts are averaged or fused by a learned combiner. What a panel is worth depends on what it is fed. We therefore have each model score each image on the five dimensions of a frozen, human-written rubric and fuse those scores, alongside each model's verdict, across model families with an out-of-fold combiner. The dimension scores measure what their labels claim: with the overall human score partialled out, a dimension prompt carries more attribute-specific information than the holistic prompt in 28 of 30 model-attribute cells. Fused, they beat the best single VLM in all ten three-family panels on EVA (against that best single model, +0.07 Spearman rho for the strongest trio and +0.10 for the pre-declared one, and +0.06 and +0.07 when averaged over twenty fold partitions; against the panel mean, the primary test gives +0.118 on its EVA design set), and on PARA they reach parity under Spearman rho and a small, non-significant loss under Kendall tau-b, where one model already captures 85% of the human noise ceiling. It is not a feature-count artefact: giving the same combiner an equal number of pure holistic columns, split from the same repetitions, does not reproduce it. The gain costs a few hundred labels, which do not transfer between datasets, and 4.8x the API calls on EVA; we report it with paired bootstraps and Kendall tau-b, alongside a failed pre-registration and the configurations that lost.

Abstract: As generative AI enters creative work, practitioners must decide where AI assistance ends and human authorship begins. Human-agent interaction (HAI) research has examined AI as a tool, collaborator, consultant, and competitor. The longitudinal problem is how these roles are revised as systems become more capable, public, and economically embedded. We report a five-year interview study with 17 Chinese digital painters, based on annual semi-structured interviews from 2021 to 2025. Participants described recurring but non-uniform patterns of protective resistance, pragmatic task delegation, and, for some, reflective agency repartitioning. Early resistance protected observation, originality, signature, and ownership from AI. Later delegation placed AI in bounded tasks such as references, backgrounds, rough sketches, and client-facing drafts. By 2025, some participants built hybrid workflows around human-only zones, while others described fatigue, precarity, or difficulty locating a remaining human role. Peer norms, emotional climates, and production pressures shaped which delegations felt useful, acceptable, or exhausting. Copyright, authorship, and creative labor remained recurring limits on what participants were willing to delegate. We frame these accounts as longitudinal agency partitioning, the situated work of deciding which stages, responsibilities, values, and claims remain human in creative human-agent interaction. We discuss design implications for revisable agency-boundary controls, provenance scaffolds, and community-facing authorship norms.

Abstract: This survey article has grown out of the human-AI co-creativity workshop organized by the authors at the ICML 2026 conference. We organized this workshop as part of a community-building effort to bring together researchers and practitioners interested in topics of generative AI, creativity, and human-AI co-creation. This article aims to provide an overview of the workshop activities and highlight several future research directions in the area of human-AI co-creativity.