Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
cs.AI, cs.CL, cs.HC, cs.LG
Submitted: 2026-06-18
Updated: 2026-08-26
Comments: Accepted to EMNLP 2026 (Industry Track)
License: http://creativecommons.org/licenses/by/4.0/
The gist: LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines.
Terminology
Abstract
LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subject-aware prompting, based on 14 pedagogical features (e.g., tutor scaffolding, student understanding) extracted from raw transcripts. We first train a prompt routing model in a simulation environment, and then deploy it for online adaptation with actual high-school students. The simulation benchmark shows the router outperforming two static baselines (0.694 vs. 0.647 and 0.64, p<0.001). A/B testing (N=656 conversations from 359 students) shows sim-to-real transfer where the model switches from analytical to scaffolding learning strategies. Our adaptive prompt selection mechanism improves instructional efficiency, maintains pedagogical quality and reduces interactions by around 3 turns (p=0.007). While a greedy router achieves a comparable exercise conversion rate with the baseline (19.1% vs. 19.6%), a stochastic router that samples strategies leads to a higher conversion rate (28.1%).
Sources
- Concrete Problems in AI Safety
- Constitutional AI: Harmlessness from AI Feedback
- Representation Degeneration Problem in Training Natural Language Generation Models
- Decoupled Weight Decay Regularization
- OpenAI GPT-5 System Card
- Proximal Policy Optimization Algorithms
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- Large Language Models Are Human-Level Prompt Engineers
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems