In interactive task learning (ITL), AI agents learn new capabilities from limited human instruction provided during task execution. STAND is a new method of data-efficient rule precondition induction specifically designed for these human-in-the-loop training scenarios. A key feature of STAND is its self-awareness of its own learning—it can provide accurate metrics of training progress back to users. STAND beats popular methods like XGBoost, decision trees, random forests, and version spaces at small-data precondition induction tasks, and is highly accurate at estimating when its performance improves on holdout examples. In our evaluations, we find that STAND shows more monotonic improvement than other models with low rates of error recurrence. These features of STAND support a more consistent training experience, enabling human instructors to estimate when they are finished training and providing active-learning support by identifying trouble spots where more training is required.

We intend to host the workshop at the EDM 2026 conference. There is a growing community of researchers at the intersection of data mining, AI, and computing education research. The objective of the CSEDM workshop is to facilitate a discussion among this research community, with a focus on how data mining can be uniquely applied in computing education research. For example, what new techniques are needed to analyze program code and CS log data? How can theoretical and empirical insights from computing education research inform the design, interpretation, and validation of data mining models? The workshop is meant to be an interdisciplinary event at the intersection of EDM and Computing Education Research. Researchers, faculty, and students are encouraged to share their AI- and data-driven methodologies, analytical frameworks, and empirical findings that demonstrate how data transforms and deepen out understanding of how students learn Computer Science (CS) skills. This full-day workshop will feature paper presentations and discussions to foster cross-disciplinary exchange and future partnerships.

We evaluate GPTutor, an LLM-powered tutoring system for an undergraduate mathematics concept course, integrating a structured proof-review tool and a conversational chatbot. In a staggered-access study with 148 students, earlier access was associated with higher homework performance, but this benefit did not transfer to exam scores. A serial mediation analysis reveals distinct pathways for the two components: lower self-efficacy predicted higher usage of both tools, but only chatbot usage constituted a negative associative pathway to subsequent exam performance, while proof-review usage showed no detectable independent association. These findings suggest that conversational LLM support alone may not reliably support transfer to independent assessment, whereas structured, work-anchored feedback showed no detectable negative association with learning outcomes.

We conducted a between-subjects experiment (N = 92) comparing three conditions in a calculus learning environment: no self-explanation (control), menu-based self-explanation, and open-ended self-explanation with LLM-generated feedback. All conditions showed positive learning gains within a fixed 60-minute practice session, with no significant between-condition differences in post-test performance. On transfer questions, the open-ended condition produced significantly higher-quality explanations than control on “Not Enough Information” (NEI) problems ( β = +11.9 β = +7.3

Culturally Relevant Pedagogy (CRP) is vital in K-12 education, yet teachers struggle to implement CRP into practice due to time, training, and resource gaps. This study explores how Large Language Models (LLMs) can address these barriers by introducing CulturAIEd, an LLM tool that assists teachers in adapting AI literacy curricula to students' cultural contexts. Through an exploratory pilot with four K-12 teachers, we examined CulturAIEd's impact on CRP integration. Results showed CulturAIEd enhanced teachers' confidence in identifying opportunities for cultural responsiveness in learning activities and making culturally responsive modifications to existing activities. They valued CulturAIEd's streamlined integration of student demographic information, immediate actionable feedback, which could result in high implementation efficiency. This exploration of teacher-AI collaboration highlights how LLM can help teachers include CRP components into their instructional practices efficiently, especially in global priorities for future-ready education, such as AI literacy.

Prompting LLMs for complex tasks (e.g., building a trip advisor chatbot) needs humans to clearly articulate customized requirements (e.g., “start the response with a tl;dr”). However, existing prompt engineering instructions often lack focused training on requirement articulation and instead tend to emphasize increasingly automatable strategies (e.g., tricks like adding role-plays and “think step-by-step”). To address the gap, we introduce Requirement-Oriented Prompt Engineering (ROPE), a paradigm that focuses human attention on generating clear, complete requirements during prompting. We implement ROPE through an assessment and training suite that provides deliberate practice with LLM-generated feedback. In a randomized controlled experiment with 30 novices, ROPE significantly outperforms conventional prompt engineering training (20% vs. 1% gains), a gap that automatic prompt optimization cannot close. Furthermore, we demonstrate a direct correlation between the quality of input requirements and LLM outputs. Our work paves the way to empower more end-users to build complex LLM applications.

We evaluate the effectiveness of LLM-Tutor, a large language model (LLM)-powered tutoring system that combines an AI-based proof-review tutor for real-time feedback on proof-writing and a chatbot for mathematics-related queries. Our experiment, involving 148 students, demonstrated that the use of LLM-Tutor significantly improved homework performance compared to a control group without access to the system. However, its impact on exam performance and time spent on tasks was found to be insignificant. Mediation analysis revealed that students with lower self-efficacy tended to use the chatbot more frequently, which partially contributed to lower midterm scores. Furthermore, students with lower self-efficacy were more likely to engage frequently with the proof-review-AI-tutor, a usage pattern that positively contributed to higher final exam scores. Interviews with 19 students highlighted the accessibility of LLM-Tutor and its effectiveness in addressing learning needs, while also revealing limitations and concerns regarding potential over-reliance on the tool. Our results suggest that generative AI alone like chatbot may not suffice for comprehensive learning support, underscoring the need for iterative design improvements with learning sciences principles with generative AI educational tools like LLM-Tutor.

Many SIGCSE attendees are either developing or using online educational tools, and all will benefit from better interoperability among these tools and better analysis of the clickstream data coming from those tools. New tools for analyzing big data leveraged by AI (e.g., deep learning for assessment) in turn improve both content and pedagogy, thus setting up a virtuous cycle fueling learning discoveries and leveraging innovation in AI: Online technologies → big data analysis → better online technologies. This NSF-supported workshop is the latest in a series of SPLICE workshops, and is a continuation of our event at SIGCSE 2023, where the SPLICE-Portal, a dedicated socio-technical research infrastructure for Computing Education Research, was presented. This year, we continue the work with several new SPLICE community working groups, including those on Dashboards, Large Language Models, Parsons Problems, and Smart Learning Content Protocols. We continue to build upon our existing collaborations developed over the course of the project to engage more members of the community in tasks that will advance the project agenda.

Large Language Models (LLMs) excel at generating content at impeccable speeds. However, they are imperfect and still make various mistakes. In Computer Science education, as LLMs are widely recognized as "AI pair programmers," it becomes increasingly important to train students on evaluating and debugging LLM-generated codes. In this work, we introduce HYPOCOMPASS, a novel system to facilitate deliberate practice on debugging, where human novices play the role of Teaching Assistants and help LLM-powered teachable agents debug code. We enable effective task delegation between students and LLMs in this learning-by-teaching environment: students focus on hypothesizing the cause of code errors, while adjacent skills like code completion are offloaded to LLM-agents. Our evaluations demonstrate that HYPOCOMPASS generates high-quality training materials (e.g., bugs and fixes), outperforming human counterparts fourfold in efficiency, and significantly improves student performance on debugging by 12% in the pre-to-post test.

We recently published a paper in this journal (de Jong et al., 2023) that presented an overview of the literature on learning in science domains through direct instruction and guided inquiry-based learning. This paper was, in part, a response to Zhang et al. (2022) who argued that the evidence firmly supported the superiority of direct instruction over inquiry learning. Sweller et al. (2024) recently replied by repeating this claim and also argued that we had ignored evidence against our position, questioned our analysis of the evidence, and claimed that direct instruction (unlike inquiry learning) is grounded in a strong theory. In this rebuttal we start by reemphasizing the conclusion from our previous paper: adequate instruction always involves different strategies, which should be thoughtfully selected based on contextual factors. Next, we demonstrate that inquiry-based learning is firmly rooted in both cognitive and socio-cultural theories of learning and conclude from recent literature that Sweller et al.‘s belief that direct instruction is overall more effective than inquiry learning is not supported by the data from empirical studies.

Many studies investigating inquiry learning in science domains have appeared over the years. Throughout this period, inquiry learning has been regularly criticized by scholars who favor direct instruction over inquiry learning. In this vein, Zhang, Kirschner, Cobern, and Sweller (2022) recently asserted that direct instruction is overall superior to inquiry-based instruction and reproached policy makers for ignoring this fact. In the current article we reply to this assertion and the premises on which it is based. We review the evidence and argue that a more complete and correct interpretation of the literature demonstrates that inquiry-based instruction produces better overall results for acquiring conceptual knowledge than does direct instruction. We show that this conclusion holds for controlled, correlational, and program-based studies. We subsequently argue that inquiry-based and direct instruction each have their specific virtues and disadvantages and that the effectiveness of each approach depends on moderating factors such as the learning goal, the domain involved, and students' prior knowledge and other student characteristics. Furthermore, inquiry-based instruction is most effective when supplemented with guidance that can be personalized based on these moderating factors and can even involve providing direct instruction. Therefore, we posit that a combination of inquiry and direct instruction may often be the best approach to support student learning. We conclude that policy makers rightfully advocate inquiry-based instruction, particularly when students’ investigations are supplemented with direct instruction at appropriate junctures.

While there is a substantial appetite in the United States for improving media consumption skills, little work has focused on the biases that can make inaccurate or misleading claims feel true. This skill is particularly difficult to teach, as effective instruction requires the instructor to adapt course content to the specific beliefs of individual students, a process that is unscalable in most classrooms. Here we examine the impact of a novel method of user-centered personalized instruction that uses value-adaptivity to highlight and address user bias in the context of a civics education game. This intervention uses estimates of player and content values to predict when players may be most susceptible to biased reasoning and then intervene in those instances. We found that the intervention successfully reduced bias among high bias-regulators with practice. These results suggest that value-adaptive systems may be able to support debiasing instruction in an effective, scalable way.

Teachers’ perspectives are critical for understanding classroom culture. They create and enforce rules in classrooms and are responsible for educating students using methods that they perceive to be most effective. Therefore, creating supplementary education technologies without understanding teachers and the culture they promote may lead to interventions that are underutilized or ineffective. Our research specifically investigates how technologies that foster student collaboration fit into teachers’ views of learning in a rural context with limited existing collaboration scaffolds. We interviewed 24 teachers and observed 39 classrooms in a rural Tanzanian village to understand how teachers value peer-peer collaboration in their teaching practice, and the unique challenges they face educating students in rural classroom settings. We uncover insights that inform the design and deployment of supplementary education technologies to support teachers in rural Tanzania and similar demographics.

As the media landscape is increasingly populated by less than reputable sources of information, educators have turned to argument evaluation training as a potential solution. Unfortunately, the bias literature suggests that our ability to objectively evaluate an argument is, to a large extent, determined by the relationship between our own beliefs and the beliefs latent in the argument we are evaluating. If the argument supports our worldview, we are much more likely to overlook logical errors. Teachers recognize this need to adapt argument evaluation instruction to the specific beliefs of students. For instance, a teacher might intentionally assign a student an argument that the student disagrees with. Unfortunately, this kind of value-adaptive instruction is infrequent due to its unscalability. We propose a novel method for data-driven value-adaptive instruction in instructional technologies. This method can be used to combat bias in real-world contexts and support human reasoning during media consumption.

Intelligent tutoring systems (ITSs) have consistently been shown to improve the educational outcomes of students when used alone or combined with traditional instruction. However, building an ITS is a time-consuming process which requires specialized knowledge of existing tools. Extant authoring methods, including the Cognitive Tutor Authoring Tools' (CTAT) example-tracing method and SimStudent's Authoring by Tutoring, use programming-by-demonstration to allow authors to build ITSs more quickly than they could by hand programming with model-tracing. Yet these methods still suffer from long authoring times or difficulty creating complete models. In this study, we demonstrate that Simulated Learners built with the Apprentice Learner (AL) Framework can be combined with a novel interaction design that emphasizes model transparency, input flexibility, and problem solving control to enable authors to achieve greater model completeness in less time than existing authoring methods.

The goal of this workshop is to bring together the existing community of researchers working on Infrastructure Design for Data-Intensive Research in Computer Science Education and a community of Learning at Scale researchers focused on Computer Science Education. While both communities share many similar goals and could greatly benefit from each other work, the interaction between the communities is small. We hope that the proposed workshop will be instrumental in bringing together like-minded researchers from different communities, establishing collaboration, and expanding the scope of infrastructure project to address critical scaling issues.