Proceedings of the Annual Meeting of the Cognitive Science Society

The creation of new ideas and content increasingly relies on collectives: not just of multiple humans, but humans and AI agents together. We study collective generation of new ideas using a controlled word-guessing task that balances open-endedness with an objective measure of task performance. Participants attempt to infer a hidden target word, scored based on the semantic similarity of their guesses to the target, while also observing the best guess from previous players. We found that hybrid human–AI groups showed higher performance than both human-only and AI-only groups. Within hybrid groups, both humans and AI agents systematically adjust their strategies relative to single-agent conditions, suggesting higher-order interaction effects, whereby agents adapt to each other's presence. Although some performance benefits can be reproduced through collaboration between heterogeneous AI systems, human–AI collaboration remains superior, underscoring complementary roles in collective creativity. Together, these findings demonstrate the advantages of human–AI synergy in collective intelligence tasks.