Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Xusen Guo, Mingxing Peng, Hongliang Lu, Hai Yang, Jun Ma, Yuxuan Liang

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.

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

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.
Paper Structure (36 sections, 14 equations, 12 figures, 5 tables, 3 algorithms)

This paper contains 36 sections, 14 equations, 12 figures, 5 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Problem Definition
  5. Framework Overview
  6. Preference-Aware Route Generation
  7. Fairness-Aware Participant Selection
  8. Negotiation-Based Route Refinement
  9. Experiments and Results
  10. Experimental Setup
  11. Datasets.
  12. Urban Attributes and Participant Profiles.
  13. Task Settings.
  14. Main Results
  15. Data Coverage utility.
  16. ...and 21 more sections

Figures (12)

  • Figure 1: Comparison of paradigms for PUS problem. (a) Conventional centralized PUS relies on simplified assumptions about participants and sensing regions. (b) MAPUS models participants as autonomous agents with personalized preferences while incorporating heterogeneous urban context. (c) AgentSense guo2025agentsense uses LLM agents as workflow components to iteratively refine a baseline PUS solution under disturbances. (d) MAPUS adopts a coordinator-and-participants multi-agent paradigm, enabling decentralized, personalized, and fairness-aware planning.
  • Figure 2: Overview of proposed MAPUS. It operates in three stages: (a) task dispatch and preference-aware route generation, (b) fairness-aware participant selection, and (c) negotiation-based route refinement.
  • Figure 3: Ablation study on the T-Drive dataset. We compare four variants of MAPUS across three different settings: w/o PRG, w/o FPS, w/o NRR, and the full model. Top: coverage utility. Bottom: path satisfaction score (PSS).
  • Figure 4: Fairness-aware participant selection analysis on the T-Drive dataset under the Medium setting. (a) Per-worker selection counts over 60 tasks, (b) CDF of selection counts, (c) data coverage utility, and (d) path satisfaction score.
  • Figure 5: Preference-aware route generation prompt.
  • ...and 7 more figures