Arapai: An Offline-First AI Chatbot Architecture for Low-Connectivity Educational Environments

• URL: http://arxiv.org/abs/2603.03339v1
• Date: Sat, 14 Feb 2026 09:53:40 GMT
• Title: Arapai: An Offline-First AI Chatbot Architecture for Low-Connectivity Educational Environments
• Abstract summary: Arapai is an offline-first AI system designed to operate entirely without internet connectivity on low-specification, CPU-only devices.<n>System integrates locally hosted, quantised language models with automatic hardware-aware model selection and pedagogically tiered response control.<n>A pilot deployment in secondary and tertiary institutions operating under limited-connectivity conditions evaluated the system across four dimensions.<n>Results indicate stable operation on legacy hardware, acceptable response times for standard instructional queries, and positive learner and teacher perceptions regarding self-directed learning support.
• Score: 0.6749750044497732
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid global expansion of large language models (LLMs) has created new opportunities for personalised and inquiry-driven learning. However, most AI chatbot systems for education rely on continuous internet connectivity, cloud infrastructure, and modern hardware. These requirements reinforce digital inequalities and limit the practical deployment of AI-supported learning in bandwidth-constrained and resource-limited environments worldwide. This paper presents Arapai, an offline-first AI chatbot architecture designed to operate entirely without internet connectivity on low-specification, CPU-only devices. The system integrates locally hosted, quantised language models with automatic hardware-aware model selection and pedagogically tiered response control. By performing inference fully on-device and maintaining models resident in memory for performance optimisation, Arapai delivers curriculum-aligned explanations, structured problem-solving support, and differentiated instructional depth without reliance on cloud services. A pilot deployment in secondary and tertiary institutions operating under limited-connectivity conditions evaluated the system across four dimensions: technical performance, usability, perceived answer quality, and educational impact. Results indicate stable operation on legacy hardware, acceptable response times for standard instructional queries, and positive learner and teacher perceptions regarding self-directed learning support. Rather than replacing cloud-based AI systems, this work proposes a complementary deployment paradigm for infrastructure-constrained education systems. The study contributes a hardware-aware architectural framework for decentralised AI tutoring and highlights the role of offline-first design in advancing digital inclusion and infrastructure-resilient educational technology.

Related papers

• AI-Model Network: Concept, Current State and Future [0.0]
  The core value of the Internet is rooted in sharing and collaboration.<n>The rapid development of the Internet, cloud computing, and big data is pushing artificial intelligence into the era of large models (LMs)<n>This paper proposes the concept, vision, and system architecture of world wide AI-model network (AI-ModelNet)
  arXiv  Detail & Related papers  (2026-05-25T13:46:21Z)
• The Accessibility Capability Boundary: Operational Limits and Expansion Potential of AI-Generated Browser-Native Accessibility Systems [0.0]
  A fundamental question emerges in accessibility computing: textithow far can AI-driven accessibility systems go?<n>This paper introduces the textitAccessibility Capability Boundary (ACB), a formal framework for reasoning about the operational limits and expansion potential of autonomous accessibility systems.<n>We ground our theoretical framework in the analysis of two real-world exploratory prototypes.
  arXiv  Detail & Related papers  (2026-05-19T10:23:48Z)
• An Experience Report on a Pedagogically Controlled, Curriculum-Constrained AI Tutor for SE Education [4.976713294177978]
  This paper presents the design and pilot evaluation of RockStartIT Tutor, an AI-powered assistant developed for a digital programming and computational thinking course within the RockStartIT initiative.<n> Powered by GPT-4 via OpenAI's Assistant API, the tutor employs a novel prompting strategy and a modular, semantically tagged knowledge base to deliver context-aware, personalized, and curriculum-constrained support for secondary school students.
  arXiv  Detail & Related papers  (2025-12-08T12:54:37Z)
• A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks [49.90474228895655]
  Cloud-edge-terminal collaborative intelligence (CETCI) is a fundamental paradigm within the artificial intelligence of things (AIoT) community.<n>CETCI has made significant progress with emerging AIoT applications, moving beyond isolated layer optimization to deployable collaborative intelligence systems.<n>This survey describes foundational architectures, enabling technologies, and scenarios of CETCI paradigms, offering a tutorial-style review for CISAIOT beginners.
  arXiv  Detail & Related papers  (2025-08-26T08:38:01Z)
• AI-Powered Math Tutoring: Platform for Personalized and Adaptive Education [0.0]
  We introduce a novel multi-agent AI tutoring platform that combines adaptive and personalized feedback, structured course generation, and textbook knowledge retrieval.<n>This system allows students to learn new topics while identifying and targeting their weaknesses, revise for exams effectively, and practice on an unlimited number of personalized exercises.
  arXiv  Detail & Related papers  (2025-07-14T20:35:16Z)
• AI Flow: Perspectives, Scenarios, and Approaches [51.38621621775711]
  We introduce AI Flow, a framework that integrates cutting-edge IT and CT advancements.<n>First, device-edge-cloud framework serves as the foundation, which integrates end devices, edge servers, and cloud clusters.<n>Second, we introduce the concept of familial models, which refers to a series of different-sized models with aligned hidden features.<n>Third, connectivity- and interaction-based intelligence emergence is a novel paradigm of AI Flow.
  arXiv  Detail & Related papers  (2025-06-14T12:43:07Z)
• Enhanced FIWARE-Based Architecture for Cyberphysical Systems With Tiny Machine Learning and Machine Learning Operations: A Case Study on Urban Mobility Systems [0.0]
  Mobility computing presents specific barriers due to its real-time requirements, decentralization, and connectivity through wireless networks. New research on edge computing and tiny machine learning (tinyML) explores the execution of AI models on low-performance devices to address these issues. This article extends a previous architecture based on FIWARE software components to implement the machine learning operations flow.
  arXiv  Detail & Related papers  (2024-11-16T13:14:29Z)
• Empowering Private Tutoring by Chaining Large Language Models [87.76985829144834]
  This work explores the development of a full-fledged intelligent tutoring system powered by state-of-the-art large language models (LLMs) The system is into three inter-connected core processes-interaction, reflection, and reaction. Each process is implemented by chaining LLM-powered tools along with dynamically updated memory modules.
  arXiv  Detail & Related papers  (2023-09-15T02:42:03Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Pervasive AI for IoT Applications: Resource-efficient Distributed Artificial Intelligence [45.076180487387575]
  Artificial intelligence (AI) has witnessed a substantial breakthrough in a variety of Internet of Things (IoT) applications and services. This is driven by the easier access to sensory data and the enormous scale of pervasive/ubiquitous devices that generate zettabytes (ZB) of real-time data streams. The confluence of pervasive computing and artificial intelligence, Pervasive AI, expanded the role of ubiquitous IoT systems.
  arXiv  Detail & Related papers  (2021-05-04T23:42:06Z)
• Towards Self-learning Edge Intelligence in 6G [143.1821636135413]
  Edge intelligence, also called edge-native artificial intelligence (AI), is an emerging technological framework focusing on seamless integration of AI, communication networks, and mobile edge computing. In this article, we identify the key requirements and challenges of edge-native AI in 6G.
  arXiv  Detail & Related papers  (2020-10-01T02:16:40Z)
• Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G Networks [84.2155885234293]
  We first summarize how to apply data-driven supervised deep learning and deep reinforcement learning in URLLC. To address these open problems, we develop a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC.
  arXiv  Detail & Related papers  (2020-02-22T14:38:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.