http://repositorio.ufc.br/handle/riufc/24013 Sun, 14 Jun 2026 09:40:54 GMT 2026-06-14T09:40:54Z http://repositorio.ufc.br/handle/riufc/86237 Título: Gerenciamento do ciclo de vida em LLMOPS: um survey sobre práticas e interações contínuas Autor(es): Sousa, Dirlia Vieira Abstract: Large Language Model Operations (LLMOps) emerges as an approach focused on managing the lifecycle of applications based on Large Language Models (LLMs), encompassing stages ranging from data preparation to deployment, monitoring, and the continuous evolution of models in production environments. Despite the recent growth of the field, the literature remains fragmented, with studies often addressing these stages in an isolated or linear manner, which hinders a comprehensive understanding of LLMOps as an integrated operational process. In this context, this work aims to analyze, through a literature survey, how the LLMOps lifecycle is addressed in existing studies, with a particular focus on practices and continuous interactions between its stages, as well as on its application across different contexts. The adopted methodology is based on systematic steps for searching, selecting, and analyzing primary studies, following predefined criteria to ensure methodological rigor and consistency in the synthesis of results. As a result, 13 studies were selected, from which it was possible to identify and analyze the main practices, processes, and continuous interactions that comprise the LLMOps lifecycle, as well as to understand its application across different domains. Tipo: TCC Thu, 01 Jan 2026 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86237 2026-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/84630 Título: ARAMIS: uma ferramenta multiagente integrada com LLM Open-Source para apoio à correção de TCCs de estudantes de graduação ARAMIS: a Multi-agent Tool Integrated Autor(es): Sousa, Gustavo Campelo de Abstract: The correction of Undergraduate Final Projects is a crucial stage in the academic development of undergraduate students. However, this process can be time-consuming and exhausting both for students during their research activities and for advisors during supervision, due to factors such as task overload and insufficiently specific feedback on research content. The automation of scientific writing correction using techniques such as Machine Learning (ML) and Natural Language Processing (NLP) has become increasingly present in students’ daily routines, especially after the emergence of Large Language Models (LLMs). In this study, Academic Review Agents for Methodological Improvements ARAMIS was developed, a tool for the analysis and correction of undergraduate theses in portuguese, composed of three specialized agents: grammatical correction, logical chaining and methodological rigor, integrating an open-source LLM guided by prompt engineering techniques. A comparative analysis approach was adopted to evaluate the feedback generation by proprietary and open-source LLMs, with the objective of selecting a model that operates with a satisfactory trade-off. The proposed solution consisted of integrating the best-performing evaluated open-source model into ARAMIS, developed within the scope of this study, focused on returning the analyzed undergraduate theses feedback in portuguese, being composed by the three agents, which serve as the core pillars of automated revision generation. The tool receives the student’s text, which is processed by the LLM and returns a structured review based on the guidelines defined in the agent’s configurations. In this work, the System Usability Scale (SUS) was employed to assess usability. The experiments were conducted with real users actively engaged in undergraduate thesis writing, and the SUS questionnaire was applied immediately after tool usage. The results demonstrate that ARAMIS achieved a score of 90.5/100, confirming that the application meets undergraduate students’s usability expectations, being useful and achieving precise and targeted feedback. Tipo: TCC Thu, 01 Jan 2026 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/84630 2026-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/82665 Título: Análise dos impactos da atuação do projeto "Preparação para a Olimpíada Brasileira de Informática em Crateús" em uma escola do ensino fundamental Autor(es): Melo, Alan Lopes Abstract: This article aims to analyze the impacts of the outreach project "Preparation for the Brazilian Computer Olympics in Crateús: Development of Logical and Computational Reasoning for Elementary School Students," which is offered by the Federal University of Ceará (UFC) in partnership with the municipal schools of Crateús-CE, in the academic training of the 6th year students of the Vilebaldo Barbosa Martins Basic Education School. This work considered how active participation in the project contributed to the development of Computational Thinking and if influenced the problem-solving ability, logical reasoning, and academic performance of students in Portuguese, Math, Science, and Religion. Furthermore, the students’ level of engagement and interest was assessed, investigating whether the experience influenced their motivation to continue participating in the Brazilian Computer Science Olympiad (OBI) and to pursue academic and professional careers in the field of computing. As a methodology, two assessments were applied along the lines of the OBI, as well as questionnaires that allowed the quantitative analysis of learning indicators and the qualitative evaluation of the perceptions of the students participating in the project. Furthermore, Pearson’s correlation coefficient was used to measure the relationship between some regular subjects and the grades obtained in the OBI simulations. The results showed that the project had a positive impact on several skills, such as reading and logical reasoning, and that participation in the project led students to improve their classroom behavior and achieve superior performance in the OBI simulations. Participants demonstrated an interest in computing and expressed their intention to pursue higher education. Furthermore, the research findings will serve to refine the project and optimize teaching strategies focused on developing Computational Thinking. Tipo: TCC Wed, 01 Jan 2025 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/82665 2025-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/82247 Título: Investigando o impacto do ensino de programação via projeto de extensão para alunos de uma escola do ensino médio Autor(es): Oliveira, Davi Martins Abstract: This article presents an investigation into the implementation of activities within an outreach project focused on teaching programming to high school students. It analyzes how programming classes influence students’ motivation to remain in school, as well as improvements in self-esteem and academic confidence. The initiative was developed by the Federal University of Ceará (UFC), in partnership with the Manoel Mano State Vocational School in Crateús/CE, where students are monitored as they participate in the Brazilian Informatics Olympiad (OBI). The methodology used to assess the project’s impact involved the application of Likert-scale questionnaires and interviews with teachers and coordinators, enabling both quantitative and qualitative analysis of the project’s effects. The results indicated significant progress in student development, with improvements in logic, thought organization, and problem-solving skills, along with increased interest in pursuing studies in the field of Computing. Educators’ reports reinforced these findings, highlighting positive changes in students’ attitudes toward learning. Based on the data analysis, it is concluded that programming education, combined with a practical and contextualized approach, can effectively contribute to students’ holistic development and strengthen educational policies aimed at school retention. Tipo: TCC Wed, 01 Jan 2025 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/82247 2025-01-01T00:00:00Z