Optimizing delivery for quick commerce factoring qualitative assessment of generated routes
This addresses cost efficiency and reliability in last-mile logistics for e-commerce, particularly in developing countries like India, but is incremental as it adds an evaluation layer to existing methods.
The study tackled the problem of limited effectiveness of vehicle routing problem (VRP) solvers in real-world last-mile delivery due to issues like unstructured addresses, by proposing a framework using large language models (LLMs) to critique routes against policy-based criteria, achieving up to 86% accuracy in identifying routing issues.
Indias e-commerce market is projected to grow rapidly, with last-mile delivery accounting for nearly half of operational expenses. Although vehicle routing problem (VRP) based solvers are widely used for delivery planning, their effectiveness in real-world scenarios is limited due to unstructured addresses, incomplete maps, and computational constraints in distance estimation. This study proposes a framework that employs large language models (LLMs) to critique VRP-generated routes against policy-based criteria, allowing logistics operators to evaluate and prioritise more efficient delivery plans. As a illustration of our approach we generate, annotate and evaluated 400 cases using large language models. Our study found that open-source LLMs identified routing issues with 79% accuracy, while proprietary reasoning models achieved reach upto 86%. The results demonstrate that LLM-based evaluation of VRP-generated routes can be an effective and scalable layer of evaluation which goes beyond beyond conventional distance and time based metrics. This has implications for improving cost efficiency, delivery reliability, and sustainability in last-mile logistics, especially for developing countries like India.