Keywords
AI agent
Project-driven teaching
Constructivist learning theory
Practical capability
Published : 2026-08-06
Abstract
To address the pain points in traditional software engineering teaching, such as disconnected learning scenarios and limited effectiveness of project-driven teaching, this study designs and implements a multi-role AI Agent named SE_Coach. It simulates roles in software development, such as product managers, and guides students through heuristic questioning and situational simulation. A 16-week controlled experiment was conducted with 80 junior computer science students. The experimental group adopted a model of teacher guidance + AI agent + group collaboration, while the control group used traditional group collaboration. The results show that the experimental group had significantly better self-efficacy and project outcome quality. SE_Coach effectively improves students’ practical abilities and collaborative thinking, providing a feasible paradigm for AI-empowered software engineering teaching.
References
Veras NL, Rocha LS, Viana W, 2021, An Authoring Tool to Support Flipped Classroom in Software Engineering Teaching. Proceedings of the 17th ACM Conference on International Computing Education Research (ICER 2021), 403–404.
Almeida C, França C, 2023, Improving the PBL Method with Experiential Learning Theory in Software Engineering Teaching. Proceedings of the 4th International Workshop on Software Engineering Education for the Next Generation (SEENG ‘22), 28–35.
Dou J, Zheng B, 2025, Construction and Innovative Application of Intelligent Agents in College EFL Teaching. Proceedings of the 2025 6th International Conference on Computer Information and Big Data Applications (CIBDA ‘25), 1324–1329.
Lyu B, Li C, Li H, et al., 2025, Exploring the Role of Teachable AI Agents’ Personality Traits in Shaping Student Interaction and Learning in Mathematics Education. In Proceedings of the 15th International Learning Analytics and Knowledge Conference (LAK ‘25). Association for Computing Machinery, New York, NY, USA, 887–894.
Lu Y, Li G, 2025, Enhancing Electric Machine Education: An Integrated Approach Using 3D-Printed Models, Multiple Intelligences, and Gamification. In Proceedings of the 2025 6th International Conference on Education, Knowledge and Information Management (ICEKIM ‘25). Association for Computing Machinery, New York, NY, USA, 1–5.
Meng TS, Po YW, Yun CC, et al., 2026, Rationalizer: Leveraging LLM to Support User Providing the Rationales Behind the Rating of Likert Scale Questionnaires. In Proceedings of the 31st International Conference on Intelligent User Interfaces (IUI ‘26). Association for Computing Machinery, New York, NY, USA, 85–105.