.png){kind=icon}
.png){kind=icon}
Return
Generative Agents for Learning Behavioral Simulation: An Interview-Driven and Multiexpert Reflection Framework
.png){kind=icon}
PRE
AI
DOI：10.1109/tlt.2026.3692781.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurately modeling and predicting student learning behaviors remains a central challenge in educational research, as traditional approaches based on surveys or learning-process traces often struggle to capture the multidimensional and latent nature of learners' motivational and strategic states. Recent advances in large language models (LLMs) and generative agents offer new opportunities to simulate learning behaviors by integrating memory construction, contextual reasoning, and expert-informed reflection. In this study, we propose a theory-grounded framework for Learning Behavioral Simulation that leverages structured interview transcripts and multiexpert reflective modeling to instantiate generative student agents. We conducted interviews with 46 preparatory mathematics students and generated domain-specific reflections, spanning educational psychology, learning sciences, educational technology, assessment, and sociocultural education, using LLM-instantiated educational expert agents. The instantiated generative student agents, informed by these expert reflections, were tasked with predicting responses on the Motivated Strategies for Learning Questionnaire, enabling construct-level evaluation of motivational and learning strategy behaviors. Experimental results show that interview-driven agents augmented with expert reflections consistently outperform persona- and demographic-based baselines. Further analysis reveals that reflections from different expert domains capture complementary dimensions of learning behavior, improving both predictive robustness and interpretability. Overall, this work demonstrates how interview-grounded memory construction and expert-guided reflection can support interpretable, scalable, and model-agnostic generative simulation of student learning behaviors, with implications for personalized and explainable educational applications.
Keywords:
Generative agent
large language model (LLM)
learning behavioral simulation
multiexpert reflection
Journal
IF:
4.9
Papers:
123
Citations:
3.0K