Friday 28 February 2025
A team of researchers has developed a novel framework for using Multi-Agent Large Language Models (LLMs) in complex engineering problem-solving, particularly in senior design projects. This innovative approach leverages the collaborative capabilities of LLMs to simulate interdisciplinary teamwork and foster critical thinking.
Traditionally, senior design projects involve students working on large-scale problems that require expertise from various fields. However, this can be challenging for students who lack experience in multiple disciplines. The new framework addresses this issue by creating a dynamic environment where students can engage with multiple perspectives and explore the complexity of decision-making in globalized engineering contexts.
The framework employs LLMs as agents that represent different expert personas, such as problem formulation agents, system complexity agents, societal and ethical agents, or project managers. These agents interact through rich, collaborative dialogues, simulating human engineering teams. The system also incorporates advanced prompting techniques to encourage more detailed and nuanced responses from the LLMs.
Researchers evaluated the effectiveness of this framework by comparing it with a single-agent system based on custom-designed metrics that align with faculty evaluation criteria. The results show that the Multi-Agent LLM framework outperforms the single-agent system in terms of technical quality, ethical considerations, social impact, and feasibility.
The study’s findings suggest that the Multi-Agent LLM framework can enhance student learning by providing more detailed responses, fostering collaboration, improving problem-solving skills, and allowing for real-time feedback through follow-up questions. The ability to simulate expert personas and respond with higher attention to details and complexity of senior design projects also offers students a deeper understanding of the ethical, technical, and social dimensions of their projects.
This innovative approach has significant implications for engineering education, as it enables students to engage with complex problems in a more structured and guided manner. The framework’s adaptability to various project types and disciplines makes it a promising tool for educators seeking to enhance student learning outcomes.
The researchers’ work highlights the potential of LLMs in educational settings, particularly in senior design projects. By leveraging the collaborative capabilities of these models, educators can create dynamic environments that simulate real-world engineering challenges, promoting critical thinking, problem-solving skills, and collaboration among students.
Cite this article: “Enhancing Senior Design Projects with Multi-Agent Large Language Models”, The Science Archive, 2025.
Multi-Agent Large Language Models, Engineering Education, Senior Design Projects, Collaborative Dialogue, Expert Personas, Problem-Solving Skills, Critical Thinking, Ethical Considerations, Social Impact, Feasibility.
