Abstract
The rapid expansion of information production presents a growing challenge in identifying high-quality, relevant studies necessary for a solid research foundation in Systematic Literature Reviews (SLR). Traditional methods often struggle with academic publications' increasing volume and dynamic nature, necessitating more efficient analytical tools. Artificial Intelligence (AI) and Natural Language Processing (NLP) offer significant potential in streamlining literature reviews through advanced analytical techniques. This work explores how AI and NLP tools enhance article screening and information synthesis, particularly through Retrieval-Augmented Generation (RAG). While large language models demonstrate strong text generation capabilities, they frequently lack comprehensive contextual understanding. RAG addresses this limitation by retrieving precise information, enabling more accurate and context-aware literature reviews. A novel approach is proposed that transforms the traditionally linear SLR workflow into a dynamic, continuously updatable bundle- a unified framework that integrates search, screening, data extraction, and synthesis. This approach is inspired by the RAPTOR Python package, which recursively embeds, clusters, and summarizes text to construct a hierarchical knowledge structure. The adapted model, DSA.VE, extends RAPTOR's capabilities to improve contextual summarization and structured synthesis, enhancing its applicability in multidisciplinary research fields. To demonstrate the effectiveness of this approach, a case study examines the potential of methanol as an alternative fuel in transport systems. The results highlight how AI-driven methodologies facilitate large-scale literature synthesis and knowledge integration. By leveraging AI, this work contributes to developing more efficient, systematic, and scalable literature review processes, addressing a critical challenge in modern research.

Abstract
ABSTRACT This study explores the impact of Green Knowledge Sharing (GKS) on Organizational Performance (OP), considering the mediating roles of Green Organizational Culture (GOC) and Technological Innovation (TI). Addressing current gaps in the literature, the research extends beyond sector-specific analyses and incorporates a cross-country perspective, examining 297 small and medium-sized enterprises (SMEs) in Portugal, Spain, and the United Kingdom. Additionally, this study acknowledges the influence of digital transformation in enhancing GKS, a factor often overlooked in previous research. By adopting a Structural Equation Modeling (SEM) approach, this article confirms a direct and positive effect on both OP and GOC, with GOC further influencing OP, establishing its mediating role in this relationship. However, the relationships between GKS and TI, as well as the indirect effect of GKS on OP through TI, are not supported. These findings offer theoretical advancements by broadening the conventional understanding of OP beyond financial metrics and present practical implications for SME managers, highlighting strategies to foster a green organizational culture and leverage technological innovation for sustainable performance.

Abstract
As recommender systems play an increasingly central role in shaping information exposure on platforms like YouTube, understanding the nature of the content they promote, especially in sensitive contexts, requires scalable and reliable labelling methods. This paper investigates the use of Large Language Models (LLM) to label YouTube videos based solely on their metadata. We propose a committee-based approach that aggregates predictions from an ensemble of seven state-of-the-art LLMs through majority voting. Using a novel dataset collected via simulated user interactions on YouTube, we analyse model agreement, labelling behavior, and the influence of model size. To assess label reliability, we also investigate the semantic coherence of label assignments. Our results show that LLM committees produce highly consistent labels in low-disagreement settings. These findings highlight both the promise and limitations of LLM-based annotation for auditing social networks.

Abstract
We study a major cyberattack at a large omnichannel grocery retailer that triggered a one-week shutdown of its online store and a corporate data breach. Using high-frequency panel data on more than 20,000 loyalty customers over 2019 and 2022, we implement a within-customer difference-indifferences design. Over the 13-week post-attack window, online transactions and online revenue both declined by approximately 10% relative to the counterfactual, with effects persisting across short-, medium-, and long-term horizons and no evidence of recovery. This contrasts with firm-level event studies, which show only short-term market reactions. The offline channel provided limited mitigation of the effects. Customers primarily substituted for alternative retailers rather than reallocating purchases within the firm, resulting in a net revenue decline for our industry partner. Effects were heterogeneous and customers with a higher concentration of online purchases, higher patronage (greater online purchase frequency and spending), and subscription ties exhibited greater shopping resilience, whereas customers with predictable shopping patterns who likely would have shopped during the affected period (and thus directly experienced the outage) were more prone to churn. This concentration of the effect among customers most likely to have been directly affected by the outage is more consistent with a substitution mechanism triggered by the disruption itself than with a generalised trust-loss interpretation, which would predict a similar response across informed customers regardless of their individual exposure to the disruption window.

Abstract
The rapid advancement of warehouse automation has increased the need for intelligent intralogistics solutions that enhance material handling efficiency and optimize space utilization. This research presents a simulation-based methodology that integrates Autonomous Mobile Robots (AMRs) with container loading optimization in a unified decision-support framework that dynamically synchronizes AMR routing with optimized truckload configurations, a feature not commonly addressed jointly in existing literature to improve warehouse operations. By leveraging a hybrid approach combining discrete event and agent-based simulation in FlexSim, the study evaluates the impact of AMR fleet size, routing strategies, and truckload configurations on overall logistics performance. A proof-of-concept industrial case study illustrates how different scenarios influence key performance metrics, such as total operation time and resource utilization. The findings demonstrate that synchronized AMR deployment and optimized container loading strategies contribute to increased throughput, reduced handling time, and enhanced logistics unit utilization. This work provides a framework for dynamic logistics planning, offering valuable insights for companies seeking to enhance warehouse efficiency and sustainability through simulation-driven decision support. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
For eight years, the Text2Story Workshop series has fostered a vibrant research community dedicated to narrative understanding, advancing shared insights into the challenges of modelling narrative structure in text. While earlier approaches laid important foundations, recent progress in Transformers and Large Language Models (LLMs) has fundamentally reshaped the field. Building on the increasing prominence of LLM-based contributions in recent editions, the ninth edition of Text2Story expands the focus toward agentic AI, where systems plan, reason, and interact over time using narratives as internal representations. Recent advances, including long-context architectures, instruction and preference-tuned models, retrieval-augmented generation, and discourse-aware prompting, have broadened the applicability of LLMs to complex narrative tasks. Nevertheless, reliably capturing fine-grained narrative structures remains challenging, particularly for event chains, temporal and causal relations, character development, and perspective consistency. These challenges are amplified in interactive and agentic settings, where narrative coherence, controllability, and reliability are critical. This edition of Text2Story explores both the opportunities and limitations of LLMs and agentic systems for narrative understanding, including the analysis of narratives generated by LLMs themselves with respect to consistency, hallucination, bias, and control. Through a diverse program of research papers, works in progress, demos, resources, and keynote talks, the workshop continues to advance narrative understanding in the era of foundation and agentic models.