AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing

TL;DR

AgentSense is a novel framework that leverages large language models and multi-agent systems to improve the adaptability and explainability of web-based participatory urban sensing, addressing limitations of existing systems.

Contribution

It introduces a training-free, multi-agent evolution system integrating LLMs for dynamic task assignment and natural language explanations in urban sensing.

Findings

Outperforms traditional methods in adaptivity and explainability.

Demonstrates robustness and transparency across large-scale datasets.

Enhances urban sensing with natural language explanations.

Abstract

Web-based participatory urban sensing has emerged as a vital approach for modern urban management by leveraging mobile individuals as distributed sensors. However, existing urban sensing systems struggle with limited generalization across diverse urban scenarios and poor interpretability in decision-making. In this work, we introduce AgentSense, a hybrid, training-free framework that integrates large language models (LLMs) into participatory urban sensing through a multi-agent evolution system. AgentSense initially employs classical planner to generate baseline solutions and then iteratively refines them to adapt sensing task assignments to dynamic urban conditions and heterogeneous worker preferences, while producing natural language explanations that enhance transparency and trust. Extensive experiments across two large-scale mobility datasets and seven types of dynamic disturbances demonstrate that AgentSense offers distinct advantages in adaptivity and explainability over traditional methods. Furthermore, compared to single-agent LLM baselines, our approach outperforms in both performance and robustness, while delivering more reasonable and transparent explanations. These results position AgentSense as a significant advancement towards deploying adaptive and explainable urban sensing systems on the web.