AI-AI co-creation outperforms human pairs in creative tasks
2026-08-10 • Computers and Society
Computers and Society
AI summaryⓘ
The authors studied how AI systems can work together to be creative, comparing setups where two AIs either had different roles or the same role, a single AI alone, and two humans working together. They found that pairs of AIs collaborating generally came up with ideas that were more creative and novel than both single AIs and human pairs. When the AIs had different roles, they produced the most useful ideas in complex tasks, showing that dividing roles helps when problems need both new ideas and practical improvements. Human teams performed the worst, likely due to common teamwork problems. This suggests that structured AI teamwork can be better at creative thinking than humans or solo AI.
AI creativityco-creationmulti-agent systemsrole differentiationhuman-AI collaborationnoveltyusefulnessiterative processgroup creativitycomplementary roles
Authors
Yingyue Luna Luan, Luning Sun, Yeun Joon Kim, Jindong Wang, Xing Xie
Abstract
Prior research often finds that AI creativity is limited: single systems rarely outperform humans, and human-AI collaboration does not exceed human output. We argue these conclusions underestimate AI's potential because most studies do not allow iterative, multi-agent exchanges that mirror the social processes underpinning human creativity. We conducted an experiment comparing four conditions: (i) AI-AI co-creation with complementary generator-evaluator roles, (ii) AI-AI co-creation with identical roles, (iii) single-AI creation, and (iv) human-human co-creation. Across three open-ended tasks, 1,212 ideas were rated by trained judges on creativity, novelty, and usefulness. Both AI-AI co-creation conditions consistently outperformed single-AI creation and human pairs on creativity and novelty. Usefulness varied by task: complementary roles yielded the most useful solutions in the broadest and most socially complex task, suggesting role differentiation is advantageous when problems require both imaginative ideation and practical refinement. Human pairs performed worst, consistent with production losses in group creativity. These findings indicate that structured, iterative multi-agent AI co-creation can exceed single-AI and human-human ideation.