https://opendata.uni-halle.de//handle/1981185920/13532 2026-10-12T12:29:39Z 2026-10-12T12:29:39Z Hansch, Kevin https://opendata.uni-halle.de//handle/1981185920/127655 2026-10-08T01:15:07Z 2026-01-01T00:00:00Z

Title: A structured literature review on drivers, enablers, and barriers of digital transformation Author(s): Hansch, Kevin Abstract: Digital transformation is influenced by numerous technological, organizational, social, and environmental factors that are described using heterogeneous terminology across the scientific literature. This paper presents a structured literature review to systematically identify, classify, and consolidate drivers, enablers, and barriers of digital transformation. Following a PRISMA 2020-guided review process, 242 publications identified in Scopus were subjected to title, abstract, and full-text screening, resulting in a final sample of 56 studies. Reported influencing factors were extracted using the terminology of the original publications, classified according to their functional role within the transformation process, and semantically consolidated. The synthesis resulted in 8 drivers, 39 enablers, and 42 barriers. While drivers constitute a comparatively concentrated set of transformation impulses, the substantially broader sets of enablers and barriers demonstrate the complexity of translating these impulses into organizational change. The findings further indicate that digital transformation is not primarily a technological challenge but depends on the interplay of technological, strategic, organizational, social, and environmental conditions. The resulting synthesis provides a structured knowledge base for analyzing the conditions that initiate, facilitate, and constrain digital transformation.

2026-01-01T00:00:00Z Ma, Da Lang, Sebastian https://opendata.uni-halle.de//handle/1981185920/125499 2026-06-19T01:09:14Z 2026-01-01T00:00:00Z

Title: Replicating research into executable knowledge Author(s): Ma, Da; Lang, Sebastian Abstract: This study presents an agentic pipeline that converts engineering research papers into callable Model Context Protocol (MCP) tools. Existing approaches such as Retrieval-Augmented Generation (RAG) can retrieve knowledge from scientific literature and generate responses for humans, but they do not address the translation of such knowledge into tools usable by a Large Language Model (LLM), leaving a gap between static literature and executable knowledge that LLM agents require. The proposed pipeline integrates PDF-to-Markdown conversion via MinerU, tool coordination through LangGraph, and MCP code synthesis using the OpenAI Codex CLI. The most suitable executable knowledge artifact is identified from the full document, which may be an algorithm, or a mathematical model. Implementation-relevant information is then extracted through the detailed-reading steps. The extracted information is consolidated into a task specification that drives the OpenAI Codex CLI to generate FastMCP-compatible MCP tools. The prototype is validated on papers containing specific algorithms and mathematical models. The proof-of- concept confirms the feasibility of converting unstructured scientific literature into usable MCP tools, and highlights the wider potential for extending callable tool libraries that enrich the LLM ecosystem.

2026-01-01T00:00:00Z Korga, Alex Maximilian Döring, Lina Reusch, Pascal https://opendata.uni-halle.de//handle/1981185920/125494 2026-06-19T01:09:12Z 2026-01-01T00:00:00Z

Title: An LLM-assisted workflow for automated literature analysis Author(s): Korga, Alex Maximilian; Döring, Lina; Reusch, Pascal Abstract: The growing volume and diversity of scientific literature pose significant challenges for systematic analysis. While systematic reviews and mapping approaches provide structured methodologies, they remain largely manual and difficult to scale. At the same time, advances in large language models (LLMs) and scholarly data infrastructures enable new opportunities for automating literature analysis. However, existing approaches often focus on isolated tasks rather than integrated workflows. This paper proposes an LLM-assisted workflow for automated literature analysis that integrates corpus construction, hybrid relevance screening, schema- guided information extraction, and human validation within a reproducible workflow structure. The approach combines automated retrieval via scholarly application programming interfaces (APIs) with a transparent scoring mechanism that integrates keyword and model- based relevance signals, as well as evidence-based extraction with traceable outputs. The workflow is evaluated using literature on automated simulation model generation as an example domain and benchmarked against a structured comparison table from an existing systematic review. The results demonstrate that the workflow can produce consistent and traceable structured outputs while reducing manual effort. At the same time, only a subset of benchmark studies could be processed automatically, reflecting the influence of data accessibility and document structure on reproducibility. Overall, the proposed workflow provides a transparent and reproducible approach to integrating LLMs into literature analysis, supporting scalable knowledge extraction while maintaining human oversight.

2026-01-01T00:00:00Z Engelhardt, Maximilian Voigt, Stefan Seeck, Stephan Lang, Sebastian https://opendata.uni-halle.de//handle/1981185920/125490 2026-06-19T01:09:25Z 2026-01-01T00:00:00Z

Title: Value of household availability profiles for last-mile routing Author(s): Engelhardt, Maximilian; Voigt, Stefan; Seeck, Stephan; Lang, Sebastian Abstract: Failed deliveries are a major challenge in last-mile logistics, increasing costs and emissions and reducing service quality. Household availability prediction offers a promising approach by aligning delivery attempts with the likelihood of successful handover. However, its real-world value remains unclear. This paper evaluates the impact of household availability profiles (APs) using empirical data and optimization-based experiments. APs are derived from the German Time Use Survey and combined with real shipment data from a German logistics service provider. Routing instances are solved using the Vehicle Routing Problem with Availability Profiles (VRPAP) under varying levels of availability information (0% 100%). Results show that increasing AP coverage significantly reduces failed deliveries and improves service performance. At the same time, travel distances remain stable, indicating no increase in routing inefficiency. However, routing costs rise due to time-based effects, particularly as waiting times are allowed and not fully captured in the cost modeling approach.

2026-01-01T00:00:00Z