Related papers: Agentic LMs: Hunting Down Test Smells
Bad smells have been defined to describe potential problems in code, possibly pointing out refactoring opportunities. Several empirical studies have highlighted that smells have a negative impact on comprehension and maintainability.…
Large Language Models (LLMs) demonstrate capabilities in code generation, potentially boosting developer productivity. However, their adoption remains limited by high computational costs, among other factors. Small Language Models (SLMs)…
Previous research has shown that journal article quality ratings from the cloud based Large Language Model (LLM) families ChatGPT and Gemini and the medium sized open weights LLM Gemma3 27b correlate moderately with expert research quality…
Norms are an important component of the social fabric of society by prescribing expected behaviour. In Multi-Agent Systems (MAS), agents interacting within a society are equipped to possess social capabilities such as reasoning about norms…
Large language models (LLMs) are increasingly used to generate software artifacts, such as source code, tests, and trace links. Requirements play a central role in shaping the input prompts that guide LLMs, as they are often used as part of…
High data quality is fundamental for today's AI-based systems. However, although data quality has been an object of research for decades, there is a clear lack of research on potential data quality issues (e.g., ambiguous, extraneous…
We develop a voice phishing (VP) detector by fine-tuning Llama3, a representative open-source, small language model (LM). In the prompt, we provide carefully-designed VP evaluation criteria and apply the Chain-of-Thought (CoT) technique. To…
In this paper, we present a tertiary systematic literature review of previous surveys, secondary systematic literature reviews, and systematic mappings. We identify the main observations (what we know) and challenges (what we do not know)…
The ever-growing popularity of mobile phones has brought additional challenges to the software development lifecycle. Mobile applications (apps, for short) ought to provide the same set of features as conventional software, with limited…
Large Language Models (LLMs) are increasingly being used to simulate human-like decision making in agent-based financial market models (ABMs). As models become more powerful and accessible, researchers can now incorporate individual LLM…
Code smells as symptoms of poor design and implementation choices. Many times they are the result of so called technical debt. Our study showed that the interest in code smells research is increasing. However, most of the publications are…
Unit tests often lack concise summaries that convey test intent, especially in auto-generated or poorly documented codebases. Large Language Models (LLMs) offer a promising solution, but their effectiveness depends heavily on how they are…
A/B testing experiment is a widely adopted method for evaluating UI/UX design decisions in modern web applications. Yet, traditional A/B testing remains constrained by its dependence on the large-scale and live traffic of human…
Fault Localization (FL) is an essential step during the debugging process. With the strong capabilities of code comprehension, the recent Large Language Models (LLMs) have demonstrated promising performance in diagnosing bugs in the code.…
Spreadsheets are commonly used in organizations as a programming tool for business-related calculations and decision making. Since faults in spreadsheets can have severe business impacts, a number of approaches from general software…
Assertion messages significantly enhance unit tests by clearly explaining the reasons behind test failures, yet they are frequently omitted by developers and automated test-generation tools. Despite recent advancements, Large Language…
Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities, making them highly successful in a variety of tasks. However, when used as agents for dealing with complex problems in…
Large-language models (LLMs) and agentic systems present exciting opportunities to accelerate drug discovery. In this study, we examine the modularity of LLM-based agentic systems for drug discovery, i.e., whether parts of the system such…
Recent advances in large language models (LLMs), make it potentially feasible to automatically refactor source code with LLMs. However, it remains unclear how well LLMs perform compared to human experts in conducting refactorings…
Deducing whodunit proves challenging for LLM agents. In this paper, we implement a text-based multi-agent version of the classic board game Clue as a rule-based testbed for evaluating multi-step deductive reasoning, with six agents drawn…