Context. LLMs have advanced code generation, but their use for generating microservices with explicit dependencies and API contracts remains understudied.Goal. We examine whether AI agents can generate functional microservices and how different forms of contextual information influence their performance.Method. We assess 144 generated microservices across 3 agents, 4 projects, 2 prompting strategies, and 2 scenarios. Incremental generation operates within existing systems and is evaluated with unit tests. Clean state generation starts from requirements alone and is evaluated with integration tests. We analyze functional correctness, code quality, and efficiency.Results. Minimal prompts outperformed detailed ones in incremental generation, with 50-76% unit test pass rates. Clean state generation produced higher integration test pass rates (81-98%), indicating strong API contract adherence. Generated code showed lower complexity than human baselines. Generation times varied widely across agents, averaging 6-16 minutes per service.Conclusions. AI agents can produce microservices with maintainable code, yet inconsistent correctness and reliance on human oversight show that fully autonomous microservice generation is not yet achievable.

The widespread adoption of machine learning (ML) has brought forth diverse models with varying architectures, data requirements, introducing new challenges in integrating these systems into real-world applications. Traditional solutions often struggle to manage the complexities of connecting heterogeneous models, especially when dealing with varied technical specifications. These limitations are amplified in large-scale, collaborative projects where stakeholders contribute models with different technical specifications. To address these challenges, we developed LoCoML, a low-code framework designed to simplify the integration of diverse ML models within the context of the Bhashini Project - a large-scale initiative aimed at integrating AI-driven language technologies such as automatic speech recognition, machine translation, text-to-speech, and optical character recognition to support seamless communication across more than 20 languages. Initial evaluations show that LoCoML adds only a small amount of computational load, making it efficient and effective for large-scale ML integration. Our practical insights show that a low-code approach can be a practical solution for connecting multiple ML models in a collaborative environment.

Cloud Operations (CloudOps) is a rapidly growing field focused on the automated management and optimization of cloud infrastructure which is essential for organizations nav-igating increasingly complex cloud environments. MontyCloud Inc. is one of the major companies in the CloudOps domain that leverages autonomous bots to manage cloud compliance, security, and continuous operations. To make the platform more accessible and effective to the customers, we leveraged the use of GenAl. Developing a GenAl-based solution for autonomous CloudOps for the existing MontyCloud system presented us with various challenges such as i) diverse data sources; ii) orchestration of multiple processes and iii) handling complex workflows to automate routine tasks. To this end, we developed MOYA, a multi-agent framework that leverages GenAI and balances autonomy with the necessary human control. This framework integrates various internal and external systems and is optimized for factors like task orchestration, security, and error mitigation while producing accurate, reliable, and relevant insights by utilizing Retrieval Augmented Generation (RAG). Evaluations of our multi-agent system with the help of practitioners as well as using automated checks demonstrate enhanced accuracy, responsiveness, and effectiveness over non-agentic approaches across complex workflows.

As Machine Learning (ML) makes its way into aviation, ML-enabled systems-including low-criticality systems-require a reliable certification process to ensure safety and performance. Traditional standards, like DO-178C, which are used for critical software in aviation, don't fully cover the unique aspects of ML. This paper proposes a semi-automated certification approach, specifically for low-criticality ML systems, focusing on data and model validation, resilience assessment, and usability assurance while integrating manual and automated processes. Key aspects include structured classification to guide certification rigor on system attributes, an Assurance Profile that consolidates evaluation outcomes into a confidence measure the ML component, and methodologies for integrating human oversight into certification activities. Through a case study with a YOLOv8-based object detection system designed to classify military and civilian vehicles in real-time for reconnaissance and surveillance aircraft, we show how this approach supports the certification of ML systems in low-criticality airborne applications.

Function calling is a complex task with widespread applications in domains such as information retrieval, software engineering and automation. For example, a query to book the shortest flight from New York to London on January 15 requires identifying the correct parameters to generate accurate function calls. Large Language Models (LLMs) can automate this process but are computationally expensive and impractical in resource-constrained settings. In contrast, Small Language Models (SLMs) can operate efficiently, offering faster response times, and lower computational demands, making them potential candidates for function calling on edge devices. In this exploratory empirical study, we evaluate the efficacy of SLMs in generating function calls across diverse domains using zero-shot, few-shot, and fine-tuning approaches, both with and without prompt injection, while also providing the finetuned models to facilitate future applications. Furthermore, we analyze the model responses across a range of metrics, capturing various aspects of function call generation. Additionally, we perform experiments on an edge device to evaluate their performance in terms of latency and memory usage, providing useful insights into their practical applicability. Our findings show that while SLMs improve from zero-shot to few-shot and perform best with fine-tuning, they struggle significantly with adhering to the given output format. Prompt injection experiments further indicate that the models are generally robust and exhibit only a slight decline in performance. While SLMs demonstrate potential for the function call generation task, our results also highlight areas that need further refinement for real-time functioning.

Architectural Knowledge Management (AKM) involves the organized handling of information related to architectural decisions and design within a project or organization. An essential artefact of AKM is the Architecture Decision Records (ADR), which documents key design decisions. ADRs are documents that capture decision context, decision made and various aspects related to a design decision, thereby promoting transparency, collaboration, and understanding. Despite their benefits, ADR adoption in software development has been slow due to challenges like time constraints and inconsistent uptake. Recent advancements in Large Language Models (LLMs) may help bridge this adoption gap by facilitating ADR generation. However, the effectiveness of LLM for ADR generation or understanding is something that has not been explored. To this end, in this work, we perform an exploratory study which aims to investigate the feasibility of using LLM for the generation of ADRs given the decision context. In our exploratory study, we utilize GPT and T5-based models with 0-shot, few-shot, and fine-tuning approaches to generate the Decision of an ADR given its Context. Our results indicate that in a 0-shot setting, state-of-the-art models such as GPT-4 generate relevant and accurate Design Decisions, although they fall short of human-level performance. Additionally, we observe that more cost-effective models like GPT-3.5 can achieve similar outcomes in a few-shot setting, and smaller models such as Flan-T5 can yield comparable results after fine-tuning. To conclude, this exploratory study suggests that LLM can generate Design Decisions, but further research is required to attain human-level generation and establish standardized widespread adoption.

Machine Learning (ML), particularly deep learning, has seen vast advancements, leading to the rise of Machine Learning-Enabled Systems (MLS). However, numerous software engineering challenges persist in propelling these MLS into production, largely due to various run-time uncertainties that impact the overall Quality of Service (QoS). These uncertainties emanate from ML models, software components, and environmental factors. Self-adaptation techniques present potential in managing run-time uncertainties, but their application in MLS remains largely unexplored. As a solution, we propose the concept of a Machine Learning Model Balancer, focusing on managing uncertainties related to ML models by using multiple models. Subsequently, we introduce AdaMLS, a novel self-adaptation approach that leverages this concept and extends the traditional MAPE-K loop for continuous MLS adaptation. AdaMLS employs lightweight unsupervised learning for dynamic model switching, thereby ensuring consistent QoS. Through a self-adaptive object detection system prototype, we demonstrate AdaMLS's effectiveness in balancing system and model performance. Preliminary results suggest AdaMLS surpasses naive and single state-of-the-art models in QoS guarantees, heralding the advancement towards self-adaptive MLS with optimal OoS in dynamic environments.

Interactive computer systems’ designers emphasize the importance of considering humans, their emotions, and behaviors as first-class entities. Emotions are integral parts of human nature, and ignoring that can lead the interactive systems to failure, low quality, or discomfort. User interfaces (UIs) are increasingly becoming adaptive to users’ various characteristics, intending to improve users’ satisfaction, performance, and decisions. However, the previous approaches proposed for supervising such adaptations are not effectively adopted in real-life problems. This paper proposes the novel approach to adapting UIs to users’ emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users’ task completion and satisfaction. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in emergency training. By taking contextual input of the users’ basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while arousing target emotions. The research includes literature analysis, surveys, and further adopting an iterative process in implementation and experimentation. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other possible UI adaptation techniques, i.e., rule-based and sequential adaptation.

Emotions are integral to human nature, and their existence, duration, and evolution could lead to specific behaviors. If emotions and behaviors are ignored in the design of socio-technical systems, they will fail or cause discomfort. User interfaces (UIs) are elements of interactive systems able to trigger or moderate emotions. UIs are increasingly designed adaptive to users' various characteristics, intending to improve their satisfaction, performance, and decisions. However, previous adaptation supervising approaches are not effectively adopted in real life since they neglect the dynamic behaviors of humans or systems. This paper proposes Emoticontrol, a quality-driven approach to adapting UIs to users' emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users' enhanced quality of experience (QoE). The approach also considers improving the software quality of service (QoS) by designing software architecture alternatives. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in evacuation training. By taking contextual input of the users' basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while keeping them emotionally controlled. We consider software performance a crucial QoS; thus, we adopt and test architectures that facilitate an acceptable level of performance. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other UI adaptation techniques.

Architecting IoT systems able to guarantee Quality of Service (QoS) levels can be a challenging task due to the inherent uncertainties (induced by changes in e.g., energy availability, network traffic) that they are subject to. Existing work has shown that machine learning (ML) techniques can be effectively used at run time for selecting self-adaptation patterns that can help maintain adequate QoS levels. However, this class of approach suffers from learning bias, which induces accuracy problems that might lead to sub-optimal (or even unfeasible) adaptations in some situations. To overcome this limitation, we propose an approach for proactive self-adaptation which combines ML and formal quantitative verification (probabilistic model checking). In our approach, ML is tasked with selecting the best adaptation pattern for a given scenario, and quantitative verification checks the feasibility of the adaptation decision, preventing the execution of unfeasible adaptations and providing feedback to the ML engine which helps to achieve faster convergence towards optimal decisions. The results of our evaluation show that our approach is able to produce better decisions than ML and quantitative verification used in isolation.

The use of IoT systems is increasing day by day. However, these systems due to their heterogeneity and inherently dynamic nature, face different uncertainties from the context, environment, etc. Such uncertainties can have a big impact on the overall system QoS, especially on energy efficiency and data traffic. This calls for better ways of architecting IoT systems that may self-adapt to keep the desired QoS. This paper presents an approach that leverages the use of machine learning (ML) techniques to perform a proactive adaptation of IoT architectures using self-adaptation patterns. It i) continuously monitors the QoS parameters; ii) forecasts possible deviations from the acceptable QoS parameters; iii) selects the best adaptation pattern based on forecasts using reinforcement learning (RL) techniques; iv) checks the quality of the selected decision using feedback mechanisms; and v) continuously performs the loop of the forecast, adaptation, and feedback. The results of our evaluations show that our approach can provide accurate QoS forecasts and further improve the energy efficiency of the system while maintaining the required data traffic.