As enrollment in CS1 courses continues to increase, extensive research has focused on autonomous support to offer personalized assistance for struggling students at scale. However, it is crucial that these intervention techniques do not inadvertently hinder the development of higher-order, computational thinking skills for novice programmers. This poster extends upon the research on LLM-based support by assessing the short- and long-term student outcomes from two carefully prompt-engineered, LLM-generated hint styles: Targeted and Socratic hints. A randomized controlled trial with 178 students was conducted over two semesters in a CS1 course at a large university, allowing students to interact with a hint generation AI agent while attempting course coding assignments. In the short-term, students receiving Socratic hints spent more time, took more attempts, and used more keystrokes to solve coding questions, while committing more repeat errors. Furthermore, this short-term loss in debugging efficiency is not counteracted by any evidence of an improvement in long-term student outcomes. Further research is being conducted to quantify the tradeoff between short-term performance and long-term, higher-order coding skill improvement in the development of educational AI agents.

Enrollments in introductory computer science (CS1) courses continue to rise, making it difficult for instructors to deliver rapid, individualized feedback that addresses students' misconceptions at scale. We present an analysis framework and instructor tool that leverage large language models (LLMs) to classify, cluster, and present students' coding errors in real time. Our approach comprises two main contributions: (1) a prompt-engineered workflow for automatic error detection and a clustering pipeline using universal sentence encoders, KMeans, and t-SNE to group errors into thematic clusters; and (2) a dashboard that enables instructors to review class-wide, LLM-identified errors and dynamically tailor instruction toward current student misunderstandings. Our automated thematic clustering system is able to surface conceptual and strategic pitfalls that often persist beneath superficial debugging. A pilot study is being conducted to evaluate the effectiveness of the dashboard tool in large-scale CS1 instructional settings to enhance active learning at scale.

Understanding the debugging process of novice programmers as they iteratively solve coding challenges is essential for developing intelligent tutoring systems that address gaps in comprehension and procedural coding skills. This poster presents a framework for systematically analyzing student coding attempts using large language models (LLMs) to identify syntactical, conceptual, and strategic errors. This study investigates 346 coding attempts for three live-coding challenges in a CS1 course, tracking the progression of errors over successive submissions. Preliminary results indicate that among students who attempted the challenges at least ten times, syntactical errors decrease more rapidly within the first ten attempts compared to conceptual or strategic errors. Although students effectively resolve syntax issues early in the debugging process, higher-level conceptual and strategic errors persist, suggesting the need for targeted instructional support at this stage.

To address the challenges of generative AI in CS1 education, especially its misuse by students to bypass coding exercises, which undermines their engagement with foundational learning, CS1 curricula are evolving to emphasize higher-level problem-solving and systems thinking. In response, a novel experiential learning initiative grounded in High-Impact Practices was introduced to a CS1 course over the course of 2 semesters, involving 132 students. This initiative utilized robotics lab assignments to enhance computational thinking across various levels of granularity, from individual functional components to overall system behaviors, bridging conceptual understanding with real-world applications. The approach emphasized project-based learning, extended engagement time, and reflective practices to deepen students' understanding of core computing concepts and scaffold knowledge integration. The curriculum featured both individual and team-based lab assignments to build foundational skills followed by collaborative problem-solving. The initiative's impact was assessed against a control group of 427 students who completed traditional web development lab assignments. Evaluation methods included thematic analyses of student reflections, instructor opinion surveys, and statistical analysis of exam performances across the semester. Results revealed a substantial positive effect on self-efficacy and learning outcomes. Students in the experiential learning group reported increased confidence in applying their computing skills to real-world scenarios, heightened engagement, and greater improvements in technical proficiency. Notably, their exam scores demonstrated a statistically significant improvement compared to the control group. These findings highlight the effectiveness of integrating practical, interactive elements into computer science education to meet the demands of a rapidly evolving technological landscape.

In the face of increasing enrollment in CS1 classes, high undergraduate teaching assistant (UTA) retention rates are necessary for a strong and sustainable teaching assistant (TA) program. However, the motivation for UTAs to ascend to more rigorous courses and the onset of boredom through fulfilling monotonous responsibilities disincentivize UTAs from staying with introductory courses for more than a few semesters. This submission reports on a unique UTA-led management model that prioritizes professional growth, facilitates leadership development, and fosters a strong community--all while enhancing the student educational experience. A three-tier organizational structure is established, assigning roles based on experience and aptitude: Head TAs oversee teams, senior TAs lead functional sub-teams, and remaining UTAs execute specialized tasks. This structure enhances professional growth through resource creation, course management, and leadership roles, while fostering a strong sense of community through mentorship and social events. UTAs contribute meaningfully to cross-functional, efficient teams, developing professional and managerial skills applicable to the workforce. A team that is enabled to express creativity to impact instructional efficiency and course management results in positive student experiences. An improved relationship between students and UTAs is directly observed, and the efficient transfer of knowledge between UTA generations results in consistency of student interactions in office hours and recitations. The UTA team is given the opportunity to blossom, and mutual relationships between the course instructors, UTAs, and students benefit the course experience and incentivize UTAs to stay.