🤖 AI Summary
This study addresses the longstanding underestimation of AI’s potential in creative tasks, attributed to the absence of multi-agent collaborative mechanisms that emulate human social creativity. The authors propose a structured, iterative multi-agent co-creation system featuring distinct generator and evaluator roles coupled with feedback loops. Evaluated across three open-ended tasks against both single-AI systems and human dyads, the framework demonstrates that AI–AI collaboration significantly outperforms baseline conditions in creativity and novelty. Notably, in the most complex task, complementary role configurations yield the most practical solutions, whereas human pairs exhibit the weakest performance. This work provides the first evidence that structured multi-agent collaboration can surpass human teamwork in creative problem-solving and underscores the critical role of functional differentiation in enhancing the practicality of outputs in complex creative tasks.
📝 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.