Does unrestricted AI access bypass the cognitive effort required for learning, or does it streamline knowledge acquisition? This paper reports on a study where we compare three designs for user-AI interaction in a learning context: (1) an unrestricted conversational bot like ChatGPT, (2) a pedagogically constrained bot that guides through hints without giving final answers, which we refer to as the Socratic mode; and (3) a non-conversational adaptive tutoring system that adjusts difficulty in real-time based on the user's cognitive engagement derived from the brain signals. Fifty study participants were tasked with learning about nuclear safety protocols, a domain chosen for its zero-prior knowledge baseline. The participants progressed through an instructional video, a pre-test, an AI-driven assessment phase, which varied in the three conditions, and an immediate post-test. The nature of the questions centered primarily on factual knowledge acquisition, but it still required participants to have a global understanding of the concepts in order to answer the questions correctly. A Muse headband was used to derive the cognitive engagement of all users in all conditions. The unrestricted chatbot produced higher learning gains (delta) than both constrained modes (p < .03, d > 0.80), while the adaptive condition generated significantly higher EEG engagement (p = .018). The cluster analysis of chatbot usage and discussion patterns by users showed that most participants in the unrestricted-mode adopted a direct answer-retrieval strategy, while participants in the Socratic-mode initially attempted to reason through the hints before progressively disengaging. Consequently, this also suggests that the success of the unrestricted AI is not an evidence of deeper learning, but rather a result of the immediate post-test evaluation after the training phase.
Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training data and stress-test tutoring systems. However, common prompt-based approaches leave the answer decision to the LLM, which tends to perform according to its built-in capabilities even when instructed to simulate a student with low mastery. As a result, these approaches may have difficulty distinguishing students with low and high levels of mastery. We demonstrate this limitation using 379 College Board-calibrated SAT Algebra items and five archetypal mastery profiles. Three LLMs from three vendors (Gemini 3.1 Flash Lite, Claude Haiku 4.5, and GPT-5.4-mini) achieve 96.8-100% accuracy across all profiles. To address this limitation, we introduce a method grounded in a Stochastic Student Knowledge Graph (SSKG). A curriculum knowledge graph (CKG) is extracted from an open algebra textbook, and each SAT solution is decomposed into a chain of required triples. The SSKG assigns a mastery probability to each triple, which is sampled to determine question correctness. An LLM then generates a first-person rationale consistent with the outcome. The simulation reduces accuracy to 44.1-85.2% across profiles and produces a clear monotone mastery gradient.
Kseniia Petukhova, Tien Dat Nguyen, Ekaterina Kochmarcs.CL
Large language models have strong potential for use in intelligent tutoring systems, but they often fail to follow effective pedagogical strategies, such as guiding students without revealing final answers. We study the application of a two-stage alignment pipeline for math mistake remediation, combining supervised fine-tuning on tutoring dialogs with Direct Preference Optimization on synthetic preference pairs. We construct a dataset that integrates existing tutoring corpora with synthetic data generated along pedagogical dimensions, such as scaffolding and factuality, and study different input configurations that incorporate solution correctness and gold answers. Experiments show that this approach improves both factual accuracy and pedagogical quality over base models and existing tutoring models. Human evaluation further indicates that our best model is competitive with a strong proprietary baseline, while providing additional benefits in terms of openness, transparency, and reproducibility. Our results highlight the effectiveness of preference-based pedagogical alignment, while also revealing challenges in reliably evaluating tutoring quality.
Agentic tutoring systems introduce a coordination challenge: multiple agents may propose different but reasonable interventions, yet only one response can be delivered to the learner. In this paper, we study how voting protocols shape cooperation among four role-constrained pedagogical agents responsible for scaffolding, misconception, motivation, and metacognition. We compare four voting protocols -- simple, ranked, cumulative, and approval voting -- across two simulated tutoring environments on SciQ and HumanEval benchmarks. Rather than using voting as a simple aggregation step, we use it to analyze how collective decision rules shape coordination under partial pedagogical conflict. Across 1,200 simulated interactions, we find that agent deliberation and voting protocol type frequently change which response ultimately wins, showing that both meaningfully shape the collective decision. Different voting rules also produce distinct coordination behaviors, and even brief tutoring turns show measurable learning gains in simulated students. Overall, we show that protocol choice is associated with distinct coordination patterns among role-specialized pedagogical agents.
This study applied the Apriori algorithm to analyze behavioral interaction patterns associated with learned helplessness (LH) in mathematics tutoring system logs. Interaction data were examined across three dimensions: LH level (low vs. high), system-based intervention (with vs. without), and problem-solving outcomes (solved vs. unsolved). The analysis of the complete dataset showed that skipping problems without using hints was the most frequent pattern linked to unsolved outcomes, while persistence behaviors such as not skipping were less dominant overall. Comparisons by LH level showed that low-LH students had stronger links between problem solving and not skipping, as well as positive associations between hint use and solved outcomes. High-LH students showed more avoidance patterns, with skipping strongly tied to unsolved outcomes. In the comparison of system-based intervention conditions, students without intervention had the highest lift for persistence-success links, while the with-intervention group had stronger patterns involving skipping behaviors leading to unsolved outcomes. Outcome-specific analysis showed that not skipping was consistently associated with solved problems across all groups, while skipping without hints predicted unsolved outcomes. Practical implications and recommendations are discussed.