CultivAgents uses three specialized AI agents to personalize gardening advice

A new research paper presents CultivAgents, a relationship-centered multi-agent system designed to provide personalized, socio-culturally grounded gardening support. Developed by Yiyang Wang and colleagues, the system is grounded in ethics of care and coordinates three specialized AI agents: an Experience Agent that adapts guidance to users’ skill levels, an Environmental Agent that grounds advice in local and seasonal conditions, and an Ethnobotanical Agent that connects plants to cultural knowledge and histories. This tripartite structure aims to overcome the generic, one-size-fits-all advice typical of existing digital gardening tools.

The team evaluated CultivAgents through a three-phase mixed-methods study involving domain experts (n=3), HCI researchers (n=7), and community gardeners (n=5). Results showed promising gains: gardener confidence rose from 3.00 to 3.60, motivation from 4.00 to 4.40, and trust in acting on AI advice from 3.20 to 4.00 (all on a 5-point scale). Participants valued hyperlocal ecological guidance and the complementary perspectives of the agents. However, the study also identified limits in cultural specificity, ecological grounding, and agent coordination. The work advances relationship-centered AI and offers design implications for systems supporting food sovereignty, community resilience, and cultural preservation.