Agentic AI for Real-Time Carbon-Aware Logistics Optimization

Kunal Kishor Sarode, Dr. Ayesha Siddique

Abstract: Because of fuel-intensive transportation methods, inefficient routing, and dynamic operational uncertainties, the logistics sector contributes significantly to global carbon emissions. In order to dynamically choose the best routes and modes of transportation, intelligent agents continuously monitor traffic conditions, fuel consumption, shipment urgency, and emissions data in this paper's novel Carbon-Aware Autonomous Logistics Optimization framework powered by Agentic AI. Three conflicting goals delivery time, operating cost, and carbon footprint are balanced by the suggested system. The framework allows logistics providers to maintain service efficiency while aligning with net-zero goals through adaptive learning and real-time decision-making. Carbon-aware routing can cut emissions by up to 18-25% without causing major delays in delivery schedules, according to experimental simulations.

Keywords: Agentic AI, Carbon-Aware Logistics, ESG, Real-Time Optimization, Sustainable Supply Chain, Multi-Objective Optimization