Glaucia Melo

Jean Douglas Carvalho, Hugo Taciro Kenji, Ahmad Mohammad Saber et al.

Advanced Driver Assistance Systems (ADAS) increasingly rely on learning-based perception, yet safety-relevant failures often arise without component malfunction, driven instead by partial observability and semantic ambiguity in how risk is interpreted and communicated. This paper presents a scenario-centric framework for reproducible auditing of LLM-based risk reasoning in urban driving contexts. Deterministic, temporally bounded scenario windows are constructed from multimodal driving data and evaluated under fixed prompt constraints and a closed numeric risk schema, ensuring structured and comparable outputs across models. Experiments on a curated near-people scenario set compare two text-only models and one multimodal model under identical inputs and prompts. Results reveal systematic inter-model divergence in severity assignment, high-risk escalation, evidence use, and causal attribution. Disagreement extends to the interpretation of vulnerable road user presence, indicating that variability often reflects intrinsic semantic indeterminacy rather than isolated model failure. These findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.

Genevieve Caumartin, Glaucia Melo

Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely on unchanged bug descriptions, which often contain noisy information, leading to poor retrieval accuracy. Recent advances in large language models (LLMs) have improved bug localization through query reformulation, yet the effect on agent performance remains unexplored. In this study, we investigate how an LLM-powered agent can improve file-level bug localization via lightweight query reformulation and summarization. We first employ an open-source, non-fine-tuned LLM to extract key information from bug reports, such as identifiers and code snippets, and reformulate queries pre-retrieval. Our agent then orchestrates BM25 retrieval using these preprocessed queries, automating localization workflow at scale. Using the best-performing query reformulation technique, our agent achieves 35% better ranking in first-file retrieval than our BM25 baseline and up to +22% file retrieval performance over SWE-agent.

Jean Douglas Carvalho, Hugo Kenji, Ahmad Mohammad Saber et al.

The integration of electric vehicles (EVs) into smart grids presents unique opportunities to enhance both transportation systems and energy networks. However, ensuring safe and interpretable interactions between drivers, vehicles, and the surrounding environment remains a critical challenge. This paper presents a multi-modal large language model (LLM)-based framework to process multimodal sensor data - such as object detection, semantic segmentation, and vehicular telemetry - and generate natural-language alerts for drivers. The framework is validated using real-world data collected from instrumented vehicles driving on urban roads, ensuring its applicability to real-world scenarios. By combining visual perception (YOLOv8), geocoded positioning, and CAN bus telemetry, the framework bridges raw sensor data and driver comprehension, enabling safer and more informed decision-making in urban driving scenarios. Case studies using real data demonstrate the framework's effectiveness in generating context-aware alerts for critical situations, such as proximity to pedestrians, cyclists, and other vehicles. This paper highlights the potential of LLMs as assistive tools in e-mobility, benefiting both transportation systems and electric networks by enabling scalable fleet coordination, EV load forecasting, and traffic-aware energy planning. Index Terms - Electric vehicles, visual perception, large language models, YOLOv8, semantic segmentation, CAN bus, prompt engineering, smart grid.

Omar Elsisi, Glaucia Melo

Conversational agents, such as chatbots and virtual assistants, have become essential in software development, boosting productivity, collaboration, and automating various tasks. This paper examines the role of adaptive AI-powered conversational agents in software development, highlighting their ability to offer dynamic, context-aware assistance to developers. Unlike traditional rule-based systems, adaptive AI agents use machine learning and natural language processing to learn from interactions and improve over time, providing more personalized and responsive help. We look at how these tools have evolved from simple query-based systems to advanced AI-driven solutions like GitHub Copilot and Microsoft Teams bots. We also explore the challenges of integrating adaptive AI into software development processes. The study aims to assess the benefits and limitations of these systems, address concerns like data privacy and ethical issues, and offer insights into their future use in the field. Ultimately, adaptive AI chatbots have great potential to revolutionize software development by delivering real-time, customized support and enhancing the efficiency of development cycles.

Glaucia Melo, Paulo Alencar, Donald Cowan

Advances in the use of cognitive and machine learning (ML) enabled systems fuel the quest for novel approaches and tools to support software developers in executing their tasks. First, as software development is a complex and dynamic activity, these tasks are highly dependent on the characteristics of the software project and its context, and developers need comprehensive support in terms of information and guidance based on the task context. Second, there is a lack of methods based on conversational-guided agents that consider cognitive aspects such as paying attention and remembering. Third, there is also a lack of techniques that make use of historical implicit or tacit data to infer new knowledge about the project tasks such as related tasks, task experts, relevant information needed for task completion and warnings, and navigation aspects of the process such as what tasks to perform next and optimal task sequencing. Based on these challenges, this paper introduces a novel paradigm for human-machine software support based on context, cognitive assistance, and machine learning, and briefly describes ongoing research activities to realize this paradigm. The research takes advantage of the synergy among emergent methods provided in context-aware software processes, cognitive computing such as chatbots, and machine learning such as recommendation systems. These novel paradigms have the potential to transform the way software development currently occurs by allowing developers to receive valuable information and guidance in real-time while they are participating in projects.

Glaucia Melo, Edith Law, Paulo Alencar et al.

Software development is a complex endeavor that depends on a wide variety of contextual factors involving a large amount of distributed information. This knowledge could include: technology-related tasks, software operating environments and stakeholder requirements. A major roadblock to using this knowledge in software development is that most of this information is implicit and captured in the developers' minds (tacit) or spread through volumes of documentation. Developers, as they work often have to maintain mental models of these tasks as they produce the software. As a result, context can be easily lost or forgotten and developers often use trial-and-error approaches while finishing the project. This study aims at analyzing whether supporting software developers with a chatbot during task execution can improve the overall development experience. The chatbot can assist the developers in executing different tasks based on implicit contextual information. We propose an implementation to explore the viability of using textual chatbots to assist developers automatically and proactively with software development project activities that recur.

Glaucia Melo, Paulo Alencar, Don Cowan

Software development is a complex activity which depends on diverse technologies and people's expertise. The approaches to developing software highly depend on these different characteristics, which are the context developers are subject to. This context contains massive knowledge, and not capturing it means knowledge is continuously lost. Although extensively researched, context in software development is still not explicit, nor proposed into a broader view of the context needed by software developers and tools. Therefore, developers' productivity is affected, as the ability to reuse this rich context is hampered. This paper proposes a literature review on context for software development, through nine research questions. The purpose of this study is making the discovered context explicit into an integrated view and proposing a platform to aid software development using context information. We believe supporting contextual knowledge through its representation and mining for recommendation and real-time provision can significantly improve big data software project development.