International Journal of Computer
Trends and Technology

Research Article | Open Access | Download PDF

Volume 73 | Issue 5 | Year 2025 | Article Id. IJCTT-V73I5P117 | DOI : https://doi.org/10.14445/22312803/IJCTT-V73I5P117

Leveraging LLMs in Logistics Tech: Automating Workflows and Enhancing Decision-Making

Mukesh Kumar

Received Revised Accepted Published
31 Mar 2025 03 May 2025 16 May 2025 31 May 2025

Citation :

Mukesh Kumar, "Leveraging LLMs in Logistics Tech: Automating Workflows and Enhancing Decision-Making," International Journal of Computer Trends and Technology (IJCTT), vol. 73, no. 5, pp. 133-143, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I5P117

Abstract

The $1 trillion logistics industry embraces Large Language Models (LLMs) to streamline workflows and sharpen decision-making for shippers, brokers, and carriers. LLMs deliver real-time freight visibility updates across all shipments—tracking or non-tracking, parsing carrier emails and EDI data to cut status delays from 24 hours to minutes, which is vital for the 20% of freight on spot markets (DAT, 2024). They process documents like bills of lading, slashing manual entry time from 30 minutes to seconds (NLP benchmarks), and flag fraud by detecting 1 in 10 invoice anomalies (Transport Topics estimate), saving $10,000 annually per 1,000 loads. LLMs analyze payment histories and reviews for carrier vetting, reducing $15,000 yearly losses from unreliable shippers (Cass Freight Index, 2023). General communications—60% of which are manual (Transport Topics, 2024)—are automated, drafting rate queries or delay alerts 50% faster, enhancing cross-party collaboration. LLMs also power a service metrics analysis and recommendation system, evaluating on-time delivery rates (e.g., 92% carrier average, DAT) and fuel costs ($3.50/gallon, EIA 2024) to suggest top carriers or routes, saving $50-$100/load. By processing dynamic inputs—12% weather delay spikes (Sea-Intelligence, 2024) or 15% fuel price swings—LLMs optimize pricing and routing decisions in real-time, boosting margins and resilience. For shippers, this means proactive load updates; for brokers, faster carrier matching; for carriers, fraud protection and vetted partners. Despite a 6-12 month integration timeline and data privacy hurdles, LLMs are transforming logistics into a connected, fraud-resistant, and data driven ecosystem, delivering measurable efficiency in a high-stakes industry.

Keywords

LLMs, logistics automation, supply chain optimization, predictive analytics, workflow automation, AI in logistics.

References

[1] Raha Aghaei et al., “The Potential of Large Language Models in Supply Chain Management: Advancing Decision-making, Efficiency, and Innovation,” arXiv preprint arXiv:2501.15411, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Sami Azirar, Hossam A. Gabbar, and Chaouki Regoui, “IQLS: Framework for Leveraging Metadata to Enable Large Language Model-based Queries to Complex, Versatile Data,” System Innovation for an Artificial Intelligence Era, 2024.
[Google Scholar] [Publisher Link]
[3] Niklas Bergman Larsson, and Jonatan Talåsen, “Applying Large Language Models in Business Processes: A Contribution to Management Innovation,” Thesis, 2024.
[Google Scholar] [Publisher Link]
[4] Roy R. Cecil et al., “Advanced Methodologies and Technologies for Innovative Information Systems,” 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Vineeta Dsouza, “Leveraging AI for Enhanced Efficiency and Automation in Business Operations,” International Journal of Computer Engineering and Technology, vol. 15, no. 4, pp. 568-576, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] E. Ferrigno, M. Rodriguez, and E. Davidsson, “Revolutionizing Drilling Operations: Next-gen LLM-AI for Real-time Support in well Construction Control Rooms,” SPE Annual Technical Conference and Exhibition, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Aidar Galimkhanov et al., “Breaking Down Silos: LLM/API Driven Experience Management Tool for Well Construction,” SPE Gas & Oil Technology Showcase and Conference, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Varun Gupta, “Leveraging AI and ML for Logistics Excellence: Case Studies and Success Strategies,” Supply Chain Transformation through Generative AI and Machine Learning, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Chao Hu et al., “Large Language Model-enabled Knowledge Exploration for Automotive Assembly Process using Ontology,” SSRN, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Saverio Ieva et al., “Enhancing Last-mile Logistics: AI-driven Fleet Optimization, Mixed reality, and Large Language Model Assistants for Warehouse Operations,” Sensors, vol. 25, no. 9, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Tamen Jadad-Garcia, and Alejandra R. Jadad, “The Foundations of Computational Management: A Systematic Approach to Task Automation for the Integration of Artificial Intelligence into Existing Workflows,” arXiv preprint arXiv:2402.05142, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Yongkuk Jeong, “Digitalization in Production Logistics: How AI, Digital Twins, and Simulation are Driving the Shift from Model based to Data-driven Approaches,” International Journal of Precision Engineering and Manufacturing-Smart Technology, vol. 1, no. 2, pp. 187-200, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Maria Johnsen, Large Language Models (LLMs), Maria Johnsen, 2024.
[Google Scholar] [Publisher Link]
[14] Samuel Kirshner, “Artificial Agents and Operations Management Decision-making,” SSRN 4726933, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Mariusz Kmiecik, “Creating a Genetic Algorithm for Third-party Logistics’ Warehouse Delivery Scheduling Via a Large Language Model,” Journal of Modelling in Management, vol. 20, no. 4, pp. 1138-1162, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Yiwei Li et al., “Large Language Models for Manufacturing,” arXiv preprint arXiv:2410.21418, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Jonas Lick et al., “Integrating Domain Expertise and Artificial Intelligence for Effective Supply Chain Management Planning Tasks: A Collaborative Approach,” Artificial Intelligence, Social Computing and Wearable Technologies, vol. 113, pp. 115-125, 2023.
[Google Scholar] [Publisher Link]
[18] Shreekant Mandvikar, “Augmenting Intelligent Document Processing (IDP) Workflows with Contemporary Large Language Models (LLMs),” International Journal of Computer Trends and Technology, vol. 71, no. 10, pp. 80-91, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] J. Matheus et al., “Revolutionizing Real-time Drilling: Leveraging Large Language Models and Retrieval-augmented Generation for Enhanced Operational Efficiency,” Offshore Technology Conference, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Tymoteusz Miller et al., “Leveraging Large Language Models for Enhancing Safety in Maritime Operations,” Applied Sciences, vol. 15, no. 3, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Abdul Khaleeq Mohammed et al., “Boosting Decision-making with LLM-powered Prompts in PowerBI,” International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, vol. 13, no. 2, 2025.
[CrossRef] [Google Scholar]
[22] Karaim Olena, “Application of LLMs for a Chatbot System in the Logistics Industry,” Ukrainian Catholic University, Faculty of Applied Sciences, Department of Computer Sciences, 2024.
[Google Scholar] [Publisher Link]
[23] Siriluk Phuengrod, Panita Wannapiroon, and Prachyanun Nilsook, “The Intelligent Collaborative Supply Chain Management with Large Language Models,” Journal of Theoretical and Applied Information Technology, vol. 103, no. 5, 2025.
[Google Scholar] [Publisher Link]
[24] Yinzhu Quan et al., “Leveraging Large Language Models for Risk Assessment in Hyperconnected Logistic Hub Network Deployment,” arXiv preprint arXiv:2503.21115, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Sumaya Abdul Rahman et al., “Leveraging Large Language Models for Supply Chain Management Optimization: A Case Study,” Innovative Intelligent Industrial Production and Logistics, pp. 175-197, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Nitin Rane, “Role and Challenges of ChatGPT and Similar Generative Artificial Intelligence in Business Management,” SSRN 4603227, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Roman Reznikov, “Enhancing Project Management Success through Artificial Intelligence,” International Journal of Multidisciplinary Research and Growth Evaluation, vol. 6, no. 1, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Maryam Shahini et al., “Leveraging Large Language Models for Cost Management and Supply Chain Optimization,” SPE Annual Technical Conference and Exhibition, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Zuber Peermohammed Shaikh, “Supply Chain Processes through Artificial Intelligence and Machine Learning: Application of Demand Planning, Reinforcement Learning, and Product Clustering,” Supply Chain Transformation through Generative AI and Machine Learning, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Ajay Singh et al., “Application of Generative AI to Derive Insight from Supply Chain & Logistics Contracts,” Abu Dhabi International Petroleum Exhibition and Conference, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Xue Song, Enhancing Human-centric Logistics Decision-making with AI-driven Route Optimization and Predictive Insights, 2025.
[Google Scholar]
[32] Jose Tupayachi et al., “Towards Next-generation Urban Decision Support Systems through AI-powered Construction of Scientific Ontology using Large Language Models: A Case in Optimizing Intermodal Freight Transportation,” Smart Cities, vol. 7, no. 5, pp. 2392-2421, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Amin Ullah et al., “The Role of LLMs in Sustainable Smart Cities: Applications, Challenges, and Future Directions,” arXiv preprint arXiv:2402.14596, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Siyu Wu et al., “Cognitive LLMs: Toward Human-like Artificial Intelligence by Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making,” Neurosymbolic Artificial Intelligence, 2024.
[Google Scholar] [Publisher Link]
[35] Yuchen Xia et al., “Incorporating Large Language Models into Production Systems for Enhanced Task Automation and Flexibility,” arXiv preprint arXiv:2407.08550, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Yimo Yan et al., “Large Language Models for Traffic and Transportation Research: Methodologies, State of the Art, and Future Opportunities,” arXiv preprint arXiv:2503.21330, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Hongke Zhao et al., “A Comprehensive Survey of Large Language Models in Management: Applications, Challenges, and Opportunities,” SSRN, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Balagopal Ramdurai, “Large Language Models (LLMs), Retrieval-augmented Generation (RAG) Systems, and Convolutional Neural Networks (CNNs) in Application Systems,” International Journal of Marketing and Technology, vol. 15, no. 1, 2025.
[Google Scholar]
[39] Balagopal Ramdurai, and Prasanna Adhithya, “The Impact, Advancements and Applications of Generative AI,” International Journal of Computer Science and Engineering, vol. 10, no. 6, pp. 1-8, 2023.
[Google Scholar]