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

2026-03-25

AI Summary

This work addresses the limitations of existing participatory urban sensing approaches, which often rely on centralized optimization and struggle to balance individual participant preferences with the heterogeneity of urban environments, resulting in rigid task allocation and insufficient fairness. To overcome these challenges, we propose MAPUS, a large language model–based multi-agent framework that models participants as autonomous agents endowed with personalized profiles and schedules. A coordinator agent is introduced to dynamically optimize task assignment and route planning through a natural language–based negotiation mechanism. Our approach pioneers the use of language-driven multi-agent negotiation in urban sensing, achieving high spatial coverage while significantly enhancing individual satisfaction and collective fairness, thereby advancing a more human-centric sensing paradigm.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Coordination and Collaboration
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Participatory urban sensing leverages human mobility for large-scale urban data collection, yet existing methods typically rely on centralized optimization and assume homogeneous participants, resulting in rigid assignments that overlook personal preferences and heterogeneous urban contexts. We propose MAPUS, an LLM-based multi-agent framework for personalized and fair participatory urban sensing. In our framework, participants are modeled as autonomous agents with individual profiles and schedules, while a coordinator agent performs fairness-aware selection and refines sensing routes through language-based negotiation. Experiments on real-world datasets show that MAPUS achieves competitive sensing coverage while substantially improving participant satisfaction and fairness, promoting more human-centric and sustainable urban sensing systems.

Problem

• participatory urban sensing
• personalization
• fairness
• heterogeneous participants
• centralized optimization

Innovation

• LLM-based multi-agent planning
• personalized urban sensing
• fairness-aware coordination
• language-grounded negotiation
• participatory sensing