Leonardo Guerreiro Azevedo

Anton Bulle Labate, Valesca Moura de Sousa, Sandro Rama Fiorini et al.

Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and Materials Science. However, large tool outputs can overflow the LLMs' context window, preventing task completion. Existing solutions such as truncation or summarization fail to preserve complete outputs, making them unsuitable for workflows requiring the full data. This work introduces a method that enables LLMs to process and utilize tool responses of arbitrary length without loss of information. By shifting the model's interaction from raw data to memory pointers, the method preserves tool functionality, allows seamless integration into agentic workflows, and reduces token usage and execution time. The proposed method is validated on a real-world Materials Science application that cannot be executed with conventional workflows, and its effectiveness is demonstrated via a comparative analysis where both methods succeed. In this experiment, the proposed approach consumed approximately seven times fewer tokens than the traditional workflow.

Maximillien de Bayser, Vinicius Segura, Leonardo Guerreiro Azevedo et al.

There is a gap in scientific information systems development concerning modern software engineering and scientific computing. Historically, software engineering methodologies have been perceived as an unwanted accidental complexity to computational scientists in their scientific systems development. More recent trends, like the end of Moore's law and the subsequent diversification of hardware platforms, combined with the increasing multidisciplinarity of science itself have exacerbated the problem because self-taught "end user developers" are not familiar with the disciplines needed to tackle this increased complexity. On a more positive note, agile programming methods have approached software development practices to the way scientific software is produced. In this work, we present the experience of a multi-year industry research project where agile methods, microservices and DevOps were applied. Our goal is to validate the hypothesis that the use of microservices would allow computational scientists to work in the more minimalistic prototype-oriented way that they prefer while the software engineering team would handle the integration. Hence, scientific multidisciplinary systems would gain in a twofold way: (i) Subject Matter Experts(SME) use their preferable tools to develop the specific scientific part of the system; (ii) software engineers provide the high quality software code for the system delivery.

Mauro Lourenço Pedra, Mônica Ferreira da Silva, Leonardo Guerreiro Azevedo

DevOps is an approach based on lean and agile principles in which business, development, operations, and quality teams cooperate to deliver software continuously aiming at reducing time to market, and receiving constant feedback from customers. However, implementing DevOps can be a complex and challenging mission due it requires significant paradigm shift. Consequently, many failures and misconceptions can occur about DevOps adoption by organizations, despite its numerous benefits. This work identifies, describes, and compares different perspectives related to DevOps adoption in academy and industry. The perspectives can be understood as factors or variables that influence or help to understand the DevOps journey. We employed a sequential multi-method research approach, including Systematic Literature Review (SLR) and Case Study. As a result, eight perspectives were found: concepts, models, principles, practices, difficulties, challenges, benefits, and strategies. More specifically, the SLR produced 390 items, which can be understood as occurrences of a perspective. The conducted case study confirmed 75 items, corroborating the SLR findings, while another 29 items emerged. This global view on DevOps adoption may guide beginners, both theorists, and practitioners, to make the necessary organizational transformation less painful.