Lina Battestilli

The variety of help that large language models (LLMs) provide has made them popular among students across fields. Computing education has been particularly affected, as LLMs can handle coding tasks effectively and provide feedback, raising hopes for supporting students while creating concerns about learning and academic integrity. Researchers have responded by developing customized tools that leverage LLMs' potential while mitigating these risks. Despite a rapidly growing body of empirical studies, no prior review has focused specifically on these purpose-built tools, where educators' pedagogical and technical design decisions are explicitly represented. We address this gap by reviewing LLM-driven, student-facing tools in undergraduate computing education, examining their pedagogical roles, technical design, evaluation methods, and impacts on learners, and discussing what they imply for the broader educational system. Drawing on PRISMA guidelines, we searched three major databases (ACM, IEEE, and ScienceDirect), conducted rigorous screening, and analyzed 52 papers. Technically, prompt engineering and multi-stage pipelines are the dominant approaches, with guardrails and prompt chaining also widely adopted, while more demanding methods such as fine-tuning remain rare. Pedagogically, most tools position the LLM as a Mentor who gives feedback on student work or a Tutor who delivers instruction, whereas roles that support metacognition, learning-by-teaching, and especially teamwork are very rare. Evaluation relies heavily on surveys and interaction logs, capturing student perceptions and usage far more often than learning outcomes, with little attention to long-term effects. Across studies, impacts on engagement and student perception are generally positive, whereas evidence for gains in learning and performance is more mixed. We argue that future work should prioritize longitudinal and learning-focused evaluation, personalization for different learners, and collaborative sensemaking and teamwork. This review offers researchers, developers, and educators a roadmap for designing and studying the next generation of AI-enhanced learning tools.

The widespread adoption of Generative AI (GenAI) tools by students across different educational levels highlights the need for them to develop robust GenAI literacy, including a working understanding of these systems' fundamental concepts, their limitations, and implications for responsible use. However, misconceptions about GenAI, such as perceiving these systems as mere search engines or database lookup systems, are commonly observed among students, while the availability of teaching resources remains fragmented, and learning objectives lack alignment. This Working Group aims to design pedagogical resources for computing science instructors, enabling them to develop students' GenAI literacy. To achieve this, the Working Group will first identify a concise set of GenAI literacy learning objectives informed by instructor experience, research literature, and community input, and subsequently design pedagogical resources aligned with these objectives.

Background and Context. Existing works in computing students' help-seeking and resource selection identified an expanding set of important dimensions that students consider when choosing a help resource. However, most works either assume a predefined list of help resources or focus on one specific help resource, while the landscape of help resources evolve at a faster speed. Objectives. We seek to study how students value each dimension in the help landscape in their resource selection and utilization processes, as well as how their identities relate to their perceptions of the landscape. Method. We surveyed N=1,625 students on their perceptions of 8 dimensions across 12 offerings of 7 courses at 2 institutions. Findings. We found a consistent pattern of four distinct dimension tiers ordered from most to least important: (1) timeliness of help, (2) availability and adaptability of the resource, (3) the resource's time/space anchor and the effort to phrase the help need, (4) formality and socialness of the resource. We also found men and first-years rate all dimensions as less important than their classmates. Implications. Our results reveal what the students collectively value most when selecting help resources and thus can inform practitioners seeking to improve their course help ecosystem.

The accessibility and effectiveness of help-seeking resources plays a pivotal role in contributing to the success of students in Computer Science courses. However, students do not always choose to utilize these resources, and when they do, their experiences can vary. While some students commend help-seeking resources for effectively providing clarification on assignment instructions, debugging code, and addressing questions about course concepts, others share instances where their problems were not resolved, or, in some cases, they did not receive any meaningful guidance from these resources. In this study, we examine the experiences of students enrolled in a CS2 course, all of whom had access to the course's help-seeking resources. These experiences were gathered through qualitative interviews at three time points within a semester. Our findings, derived from emergent coding, reveal thematic patterns in student encounters with help-seeking resources and contribute to a broader theme regarding help-seeking resource utilization at different phases of the semester. The findings of this investigation contribute to the wider conversation on student success and help-seeking resource utilization in Computer Science education.