CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening

2026-05-21

AI Summary

This study addresses the limitations of existing digital horticultural tools, which often neglect users’ skill levels, local ecologies, seasonal dynamics, and cultural contexts, thereby failing to deliver contextually relevant support. To bridge this gap, the authors propose a relational multi-agent system that integrates care ethics into AI design for the first time. The system coordinates three specialized agents—experiential, environmental, and ethnobotanical—to synthesize user modeling, localized ecological data, and an ethnobotanical knowledge base, generating personalized gardening recommendations aligned with individual capabilities, regional conditions, and cultural frameworks. Empirical results demonstrate significant improvements in user confidence (3.00→3.60), motivation (4.00→4.40), and trust in AI-generated advice (3.20→4.00), effectively fostering situated horticultural practices that advance food sovereignty, community resilience, and cultural heritage.

Abstract

Gardening is critical to support well-being, cultural continuity, and food autonomy, yet existing digital tools often provide generic advice that overlooks gardeners' skills, local ecologies, seasons, and cultural contexts. We introduce CultivAgents, a relationship-centered multi-agent system for personalized, socio-culturally grounded gardening support. Grounded in ethics of care, CultivAgents coordinates multiple specialized 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. We evaluated CultivAgents through a three-phase mixed-methods study with domain experts (n=3), HCI researchers (n=7), and community gardeners (n=5), analyzing expert feedback, pre/post surveys, and participatory design activities. Results suggest that CultivAgents helped gardeners translate interest into situated action: community gardeners reported increased confidence (3.00 to 3.60), motivation (4.00 to 4.40), and trust in acting on AI advice (3.20 to 4.00). Participants valued hyperlocal ecological guidance and complementary agent perspectives, while also identifying limits in cultural specificity, ecological grounding, and agent coordination. The work advances relationship-centered AI, offering design implications for multi-agent systems that support food sovereignty, community resilience, and cultural preservation.

Problem

• personalized gardening
• multi-agent systems
• cultural context
• local ecology
• digital tools

Innovation

• relationship-centered AI
• multi-agent system
• personalized gardening
• ethics of care
• socio-culturally grounded