Purpose: Dissertations from the University of Novi Sad (UNS) are integrated with the research information system called the current research information system (CRIS) UNS. This paper aims to present a proposal for an extension of this system to enable the storage of student papers as prescribed by PhD study exam obligations. The proposed extension enables preservation and improves discoverability of scientific and technical works produced by students during their PhD studies.Design/methodology/approach: An analysis of examination modes in accredited PhD study programs has been conducted. It was noted that students in examination modes verify the obtained results in the form of scientific and technical work. The main idea of this paper is to enable the preservation of those student results and to implement electronic services for retrieving those results by current and future PhD students to empower the development of science.Findings: The proposal includes an extension of the CRIS UNS to store and publish student papers as prescribed as a PhD study exam obligation; an extension of the CERIF data model to enable storing of student papers; cataloguing student papers in the MARC 21 format; and a way to represent student papers in the Dublin Core format.Practical implications: This paper can be a starting point for initiatives for the creation of institutional, regional, national and international Web portals for searching and browsing papers by PhD students.Social implications: This system offers the improvement of cooperation between PhD students from different institutions and countries.Originality/value: The paper presents an extension of institutional, national and international current research information system (CRIS) systems which will enable the preservation and improve discoverability of student papers produced during PhD studies. The proposed extension has been verified by its implementation within the CRIS UNS system, which also supports monitoring of the scientific competencies of students based on an automatic evaluation of published scientific results.

The process of discovering appropriate resources in digital libraries within universities is important, as it can have a big effect on whether retrieved works are useful to the requester. The improvement of the user experience with the digital library of the University of Novi Sad dissertations (PHD UNS) through the personalization of search results representation is the aim of the research presented in this paper. There are three groups of PHD UNS digital library users: users from the academic community, users outside the academic community, and librarians who are in charge of entering dissertation data. Different types of textual and visual representations were analyzed, and representations which needed to be implemented for the groups of users of PHD UNS digital library were selected. After implementing these representations and putting them into operation in April 2017, the user interface was extended with functionality that allows users to select their desired style for representing search results using an additional module for storing message logs. The stored messages represent an explicit change in the results representation by individual users. Using these message logs and ELK technology stack, we analyzed user behavior patterns depending on the type of query, type of device, and search mode. The analysis has shown that the majority of users of the PHD UNS system prefer using the textual style of representation rather than the visual. Some users have changed the style of results representation several times and it is assumed that different types of information require a different representation style. Also, it has been established that the most frequent change to the visual results representation occurs after users perform a query which shows all the dissertations from a certain time period and which is taken from the advanced search mode; however, there is no correlation between this change and the client’s device used.

This paper presents SPARK_AI, a prompt-orchestrated system architecture for governing how large language models (LLMs) conduct structured and adaptive reasoning in human–AI interaction. The framework mitigates ad hoc LLM use by replacing direct answer generation with a process-oriented, step-by-step reasoning workflow. We focus on SPARK_AI_MATH, a domain module that supports learners in solving non-routine problem-solving tasks by operationalizing well-established problem-solving phases and guided questioning dialog strategies (Socratic-style prompts), with an optional tool-mediated visualization layer (e.g., GeoGebra). The module implements a five-phase conversational protocol consisting of problem interpretation, analysis of givens, planning, execution, and reflection, together with a controlled hint policy. This design is realized through a stateful system architecture in which each problem instance is maintained as an independent interaction track with a persistent reasoning state. User acceptance was evaluated by first-year mechanical engineering students (N = 108) using an expanded Technology Acceptance Model instrument, and the results were analyzed via PLS-SEM. The findings indicate overall favorable perceptions, with perceived usefulness and learning support emerging as key predictors of intention for continued use. Beyond this specific domain, the SPARK_AI framework enables efficient domain adaptation through localized prompt strategies while preserving a shared cognitive control layer for reasoning-centered human–LLM interaction.