Papers

Papers Logistics & Transportation Networks

Deep Learning–Accelerated MSLNS Reduces Optimality Gap to Less Than 2%

Haohui Zhang, Wouter van Heeswijk, and colleagues present a novel approach to real-time freight bundling using a Deep Learning–accelerated Multi-Start Large Neighborhood Search (MSLNS). Their method significantly reduces the optimality gap to less than 2%, outperforming state-of-the-art baselines in both solution quality and runtime.

2026-10-05

Papers Logistics & Transportation Networks

Transforming Imagination into Viable Solo Business: A 3-Stage Framework with AI

This paper by Farhad Rezazadeh and Pegah Bonehgazy explores how individual entrepreneurs can leverage AI agents to transform creative ideas into successful solo businesses. The authors propose a three-stage framework—imagination shaping, reality testing, and reality scaling—highlighting the role of AI in each stage.

2026-10-04

Papers Digital, Intelligence & Platforms

GraphRAG Enhances LLMs with Improved Domain-Specific Reasoning

This paper surveys the advancements in Graph Retrieval-Augmented Generation (GraphRAG) for customizing large language models (LLMs) in specialized domains. It addresses the limitations of traditional RAG systems and highlights key innovations, including graph-structured knowledge representation, efficient graph-based retrieval, and structure-aware knowledge integration.

2026-10-03

Papers

AI-Enhanced TOE Framework Boosts Industrial and Environmental Performance in Fragile Economies

This study by Shaima Farhana, Dong Yu, and colleagues investigates the impact of integrating AI into the Technology-Organization-Environment (TOE) framework on industrial and environmental performance in fragile and transforming economies, focusing on Yemen and Saudi Arabia. The research reveals significant positive effects, with AI-TOE enhancing both environmental and manufacturing performance, and highlights the need for context-specific AI adoption strategies.

2026-10-02

Papers Digital, Intelligence & Platforms

FDDM Enhances Osteosarcoma Assessment with 10% mIOU Improvement

Osteosarcoma, a common primary bone cancer, requires accurate necrosis assessment for effective treatment. Manual assessments are subjective and prone to variability. FDDM, a novel framework by Manh Duong Nguyen, Dac Thai Nguyen, et al., integrates patch classification and region-based segmentation using foundation and discrete diffusion models, achieving up to a 10% improvement in mIOU and 32.12% in necrosis rate estimation.

2026-10-01

Papers Risk & Resilience

Enhancing Supply Chain Visibility with Federated Learning and Graph Neural Networks

Ge Zheng and Alexandra Brintrup propose a novel approach using Federated Learning (FL) and Graph Convolutional Neural Networks (GCNs) to enhance supply chain visibility. Their method addresses data privacy, security, and regulatory concerns while providing comprehensive insights into supply chain dynamics.

2026-09-30

Papers Logistics & Transportation Networks

AI-Driven Dynamic Route Optimization and Autonomous Delivery Systems: Enhancing Logistics Efficiency

This paper explores the transformative impact of AI in logistics, focusing on dynamic route optimization and autonomous delivery systems. It highlights how AI can enhance efficiency, reduce costs, and improve service delivery, while also addressing the challenges and limitations of these technologies.

2026-09-29

Papers

Securing Agentic AI: Addressing Key Vulnerabilities in Autonomous Agents

This paper explores the multifaceted security challenges in agentic AI, focusing on prompt injection, memory poisoning, tool integrity, inter-agent communication, and model routing. The authors highlight the need for a holistic approach to ensure the integrity and provenance of autonomous agents, particularly in critical domains like supply chain management.

2026-09-28

Papers Logistics & Transportation Networks

Venture Capital Investments and Syndication Networks: Central Network Positions Expand Distant Investments

This paper by Olav Sorenson and Toby E. Stuart examines how interfirm networks in the U.S. venture capital (VC) market influence the spatial distribution of investments. The study reveals that venture capitalists with central positions in syndication networks are more likely to invest in spatially distant companies, expanding their investment radius.

2026-09-27

Papers Digital, Intelligence & Platforms

A Comprehensive Survey on MLOps Tool Support for Efficient ML Lifecycle Management

This paper provides a detailed survey of MLOps tool support, focusing on the integration of Machine Learning (ML) practices with DevOps principles. The study evaluates various tools, including Kubeflow, MLFlow, DataRobot, and others, highlighting their features, limitations, and practical implications for efficient ML lifecycle management.

2026-09-26

Papers Digital, Intelligence & Platforms

Knowledge Graphs: Enhancing Supply Chain with Improved Accuracy in QA

This paper, authored by Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and Philip S. Yu, provides a comprehensive review of knowledge graphs (KGs) and their applications. The authors explore the representation, acquisition, and use of KGs, highlighting their potential to enhance decision-making in the supply chain through improved accuracy in question answering (QA) and other AI-driven tasks.

2026-09-25

Papers Digital, Intelligence & Platforms

Neural Combinatorial Optimization for Vehicle Routing: A 4-Category Framework

This paper provides a comprehensive survey of Neural Combinatorial Optimization (NCO) algorithms for solving Vehicle Routing Problems (VRPs), categorizing them into four distinct types: Learning to Construct (L2C), Learning to Improve (L2I), Learning to Predict-Once (L2P-O), and Learning to Predict-Multiplicity (L2P-M). The study highlights the current limitations and future directions in NCO, aiming to enhance the efficiency and scalability of VRP solutions.

2026-09-23