arXiv:2607. 09745v1 Announce Type: new Abstract: This paper introduces SupplyNetPy, an open-source, well-documented Python library for modeling and discrete-event simulation of supply chain networks with arbitrary multi-echelon structures.
arXiv:2607. 16769v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems.
For years, supply chain planning at e-commerce firms has operated as a collection of isolated projects. Each planning task from static network planning to dynamic warehouse assortment planning requires analysts to spend weeks building models from scratch, calibrating and persuading executives to act on outputs they cannot verify.
arXiv:2607. 21354v1 Announce Type: new Abstract: For years, supply chain planning at e-commerce firms has operated as a collection of isolated projects.
The article "Supply Chain Analytics: A Data-Driven Approach" presents a mathematically rigorous framework that integrates statistical learning with robust decision-making for logistics and operations management. It covers topics from empirical demand forecasting to optimal inventory and network control under uncertainty, including sample minimization, dynamic programming for inventory replenishment, network fulfillment, and distributionally robust optimization using transport theory. The work also links predictive models with prescriptive algorithms such as column generation for vehicle routing and non‑homogeneous queueing regimes, offering both theoretical foundations and algorithmic guidance for building resilient, automated supply chain systems.
arXiv:2605. 12768v2 Announce Type: replace-cross Abstract: Open time-series forecasting (TSF) benchmarks cover retail, energy, weather, and traffic, but supply-chain logistics remains underserved.
arXiv:2607. 28488v1 Announce Type: cross Abstract: Can supply-chain AI move beyond isolated decision modules toward unified operational planning?
The paper introduces a constraint‑aware conditional generative framework for creating synthetic origin‑destination demand data in hierarchical logistics networks. By modeling demand as a conditional distribution over destinations given each origin, the method incorporates differentiable operational constraints directly into the generative objective, allowing topology‑aware synthesis that remains operationally feasible. Experiments on industrial fulfillment and transportation networks show a 16% performance gain over graph neural network baselines, 87% operational compliance, and efficient cold‑start adaptation, supporting capacity planning, network design evaluation, and routing optimization.
The study explores machine learning and deep learning techniques to predict travel time for transportation and logistics within supply chain systems. By leveraging extensive historical data, it aims to build an accurate model that estimates travel times for inventory movement. The research emphasizes the importance of precise travel time predictions for improving logistics consistency, performance, and planning across the supply chain.
arXiv:2609.13561v1 Announce Type: new Abstract: Efficient utilization of supply chain analytics for decision making remains a significant challenge for planners, as critical tasks such as database qu...
arXiv:2605.14259v3 Announce Type: replace Abstract: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning....
arXiv:2606. 26852v1 Announce Type: new Abstract: Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing.
The paper presents a graph‑constrained agentic framework that enables large language models to adapt retail supply‑chain decision modules to evolving requirements. It jointly selects intervention routes and admissible module changes, validating candidates against downstream KPIs. Experiments with 100 warehouse requirements and three LLMs show the framework improves end‑to‑end success from 72–76% to 79–83%.