Related papers: Object-Oriented Program Comprehension: Effect of E…
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…
Unlike traditional automation tools or static LLM-based systems, agents combine decision-making and tool utilization to accomplish complex tasks, showing great potential in software engineering. However, existing studies largely focus on…
Expert persona prompting -- assigning roles such as expert in math to language models -- is widely used for task improvement. However, prior work shows mixed results on its effectiveness, and does not consider when and why personas should…
A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature space (also known as attribute-value descriptions). A teacher…
Continuous practices are a staple of the modern software development workflow. Automation, in particular, is widely adopted due to its benefits related to quality and productivity. However, automation, similarly to all other aspects of the…
This work aims at the goal whether the artificial intelligence can recognize phase transition without the prior human knowledge. If this becomes successful, it can be applied to, for instance, analyze data from quantum simulation of…
In many fields$\unicode{x2013}$including genomics, epidemiology, natural language processing, social and behavioral sciences, and economics$\unicode{x2013}$it is increasingly important to address causal questions in the context of factor…
Program synthesis aims to automatically generate an executable program that conforms to the given specification. Recent advancements have demonstrated that deep neural methodologies and large-scale pretrained language models are highly…
The prevailing assumption in agent orchestration is that more context is better. We test this on multi-agent software design across 10 tasks, 7 context-injection conditions, and over 2,700 runs, and find a crossover effect: the same…
We present a document-level neural machine translation model which takes both source and target document context into account using memory networks. We model the problem as a structured prediction problem with interdependencies among the…
This research full paper investigates the factors influencing computing educators' adoption of project-based learning (PjBL) in software engineering and computing curricula. Recognized as a student-centered pedagogical approach, PjBL has…
We describe a computational model of humans' ability to provide a detailed interpretation of components in a scene. Humans can identify in an image meaningful components almost everywhere, and identifying these components is an essential…
Developers interrupting their participation in a project might slowly forget critical information about the code, such as its intended purpose, structure, the impact of external dependencies, and the approach used for implementation.…
Novice programmers experience emotional difficulties in informal online learning environments, where confusion and frustration can hinder motivation and learning outcomes. This study investigates novice programmers' emotional experiences in…
Process models constitute crucial artifacts in modern information systems and, hence, the proper comprehension of these models is of utmost importance in the utilization of such systems. Generally, process models are considered from two…
We propose Object-oriented Neural Programming (OONP), a framework for semantically parsing documents in specific domains. Basically, OONP reads a document and parses it into a predesigned object-oriented data structure (referred to as…
Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods ineffective in this context. In this paper, we introduce a novel…
In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…
Well structured and readable source code is a pre-requisite for maintainable software and successful collaboration among developers. Static analysis enables the automated extraction of code complexity and readability metrics which can be…
As large language models have evolved, it has become crucial to distinguish between process supervision and outcome supervision -- two key reinforcement learning approaches to complex reasoning tasks. While process supervision offers…