StoryLensEdu: Personalized Learning Report Generation through Narrative-Driven Multi-Agent Systems

TL;DR

Evaluation with real users shows that StoryLensEdu enhances engagement and promotes a deeper understanding of the learning process, and supports post-generation interactive question answering to improve explainability and user engagement.

Abstract

Personalized feedback plays an important role in self-regulated learning (SRL), helping students track progress and refine their strategies. However, current common solutions, such as text-based reports or learning analytics dashboards, often suffer from poor interpretability, monotonous presentation, and limited explainability. To overcome these challenges, we present StoryLensEdu, a narrative-driven multi-agent system that automatically generates intuitive, engaging, and interactive learning reports. StoryLensEdu integrates three agents: a Data Analyst that extracts data insights based on a learning objective centered structure, a Teacher that ensures educational relevance and offers actionable suggestions, and a Storyteller that organizes these insights using the Heroes Journey narrative framework. StoryLensEdu supports post-generation interactive question answering to improve explainability and user engagement. We conducted a formative study in a real high school and iteratively developed StoryLensEdu in collaboration with an e-learning team to inform our design. Evaluation with real users shows that StoryLensEdu enhances engagement and promotes a deeper understanding of the learning process.

Figures (12)

• Figure 1: Learning objective graph with three types of objectives.
• Figure 2: System Overview. The system takes student learning data (a) structured around a learning objective graph (b), which is analyzed by the Data Analyst agent (c) to generate diagnostic insights and visualizations. These are embedded into an annotated objective graph, then interpreted by the Teacher agent (d) to produce pedagogically grounded feedback. The Storyteller agent (e) organizes the content into narrative components using a Hero’s Journey structure and composes the personalized learning report (f). Users can interact with the report (g) to explore details and access contextual explanations (h).
• Figure 3: Report example. The left sidebar serves as an interactive index for rapid navigation, while the right pane displays detailed content.
• Figure 4: (A) Choose a visual selection tool (e.g., box or lasso). (B) Brush to choose the data points of interest. (C) Type the question and then submit it. (D) The agent retrieves related data from the database to generate the answer, and returns textual and visual elements.
• Figure 5: Questionnaire results in the user study for 10 students (S1 - S10) and 4 teachers (T1 - T4).