Language-Grounded Multi-Agent Planning for Personalized and Fair Participatory Urban Sensing

1. 1Model participants as autonomous agents with personal preferences
2. 2Use LLMs to generate personalized task assignments
3. 3Implement a multi-agent planning framework to optimize task allocation
4. 4Evaluate the framework's performance in terms of fairness and efficiency

This research benefits data scientists and AI engineers working on urban sensing projects, as it provides a novel approach to personalized and fair data collection

💡 LLMs can be used to generate personalized task assignments in participatory urban sensing, leading to more fair and efficient data collection

🚀 MAPUS: a novel LLM-based framework for personalized & fair urban sensing #AI #urbanplanning