Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)

TL;DR

This paper introduces log-contextualized RAG (LC-RAG), a method that uses environment logs to improve personalized, context-aware responses in student-agent interactions, enhancing critical thinking support.

Contribution

The paper presents LC-RAG, a novel approach that leverages environment logs to improve retrieval and personalization in collaborative dialogue systems for education.

Findings

LC-RAG outperforms discourse-only retrieval baselines.

Copa agent provides relevant, personalized guidance.

Supports students' critical thinking and epistemic decisions.

Abstract

Collaborative dialogue offers rich insights into students' learning and critical thinking, which is essential for personalizing pedagogical agent interactions in STEM+C settings. While large language models (LLMs) facilitate dynamic pedagogical interactions, hallucinations undermine confidence, trust, and instructional value. Retrieval-augmented generation (RAG) grounds LLM outputs in curated knowledge, but requires a clear semantic link between user input and a knowledge base, which is often weak in student dialogue. We propose log-contextualized RAG (LC-RAG), which enhances RAG retrieval by using environment logs to contextualize collaborative discourse. Our findings show that LC-RAG improves retrieval over a discourse-only baseline and enables our collaborative peer agent, Copa, to deliver relevant, personalized guidance that supports students' critical thinking and epistemic decision-making in the collaborative computational modeling environment C2STEM.