Bridging Policy and Real-World Dynamics: LLM-Augmented Rebalancing for Shared Micromobility Systems

TL;DR

This paper presents AMPLIFY, an LLM-augmented framework that dynamically adapts vehicle rebalancing strategies in shared micromobility systems to handle emergent events, improving demand satisfaction and revenue.

Contribution

The paper introduces a novel LLM-based adaptation module that enhances rebalancing policies for micromobility, addressing emergent scenarios often overlooked by existing methods.

Findings

Improves demand satisfaction in real-world data

Increases system revenue compared to baseline policies

Demonstrates effective real-time adaptation in emergent events

Abstract

Shared micromobility services such as e-scooters and bikes have become an integral part of urban transportation, yet their efficiency critically depends on effective vehicle rebalancing. Existing methods either optimize for average demand patterns or employ robust optimization and reinforcement learning to handle predefined uncertainties. However, these approaches overlook emergent events (e.g., demand surges, vehicle outages, regulatory interventions) or sacrifice performance in normal conditions. We introduce AMPLIFY, an LLM-augmented policy adaptation framework for shared micromobility rebalancing. The framework combines a baseline rebalancing module with an LLM-based adaptation module that adjusts strategies in real time under emergent scenarios. The adaptation module ingests system context, demand predictions, and baseline strategies, and refines adjustments through self-reflection. Evaluations on real-world e-scooter data from Chicago show that our approach improves demand satisfaction and system revenue compared to baseline policies, highlighting the potential of LLM-driven adaptation as a flexible solution for managing uncertainty in micromobility systems.