Search and Filter

Arapai: An Offline-First LLM Architecture For Adaptive Learning In Low-Connectivity Environments

Date

AI Overview

Why it matters

Most AI learning systems require continuous internet and cloud computing. This reliance limits their use in bandwidth-constrained environments.

Study at a glance
  • Question: Can an offline-first language model system effectively support learning on low-specification devices in limited-connectivity environments?
  • Setting and data: 120 students and 9 instructors from secondary and tertiary institutions, tested under limited-connectivity conditions.
  • Method: System development and user evaluation on legacy hardware.
  • AI tools: Arapai
Key findings
  • The system operated stably on legacy, CPU-only hardware without relying on cloud infrastructure.
  • Typical user queries achieved acceptable response times of 1 to 3 seconds.
  • Students and instructors reported positive perceptions of the tool's effectiveness in supporting self-directed learning.

Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.

Artificial intelligence and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalised explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents Arapai, an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification, CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. The system was evaluated with 120 students and 9 instructors from secondary and tertiary institutions under limited-connectivity conditions. Results indicate stable operation on legacy hardware, acceptable response times of 1-3 seconds for typical queries, and positive user perceptions of its effectiveness in supporting self-directed learning.