Margaret Ellis

Margaret Ellis, Nikitha Donekal Chandrashekar, Sehrish Basir Nizamani et al.

Student access to Large Language Models (LLMs) is reshaping learning behaviors; at the same time students are entering the workforce where effective LLM use is becoming an expected skill. In this Experience Report we share our DURA framework (Demystify-Use-Reflect-Assess) and materials we used to restructure our CS2 course to allow the use of LLMs. We first demystified LLMs, then provided guidance on use with required attribution. We also added reflections related to LLM use at three points throughout the semester to encourage student meta-cognition around LLM use. We increased the value of proctored assessments in tandem with allowing retakes and including questions that explicitly assess skills from programming assignments. Students reported using LLMs for clarifying course concepts, debugging, understanding assignment guidelines, and determining test cases, but also still sought assistance via office hours and TAs, monitored Piazza, and reviewing course content. Students articulated thoughtful and strategic approaches to LLM use and also valued the instructional content and guidance from course staff. Student use of office hours increased slightly this semester and student perceptions that the instructor cares about them and their learning improved.

Nikitha Donekal Chandrashekar, Sehrish Basir Nizamani, Margaret Ellis et al.

We transitioned our post-CS1 course that introduces various subfields of computer science so that it integrates Large Language Models (LLMs) in a structured, critical, and practical manner. It aims to help students develop the skills needed to engage meaningfully and responsibly with AI. The course now includes explicit instruction on how LLMs work, exposure to current tools, ethical issues, and activities that encourage student reflection on personal use of LLMs as well as the larger evolving landscape of AI-assisted programming. In class, we demonstrate the use and verification of LLM outputs, guide students in the use of LLMs as an ingredient in a larger problem-solving loop, and require students to disclose and acknowledge the nature and extent of LLM assistance. Throughout the course, we discuss risks and benefits of LLMs across CS subfields. In our first iteration of the course, we collected and analyzed data from students pre and post surveys. Student understanding of how LLMs work became more technical, and their verification and use of LLMs shifted to be more discerning and collaborative. These strategies can be used in other courses to prepare students for the AI-integrated future.

Asif Rahman, Veljko Cvetkovic, Kathleen Reece et al.

Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6\% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9\% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.