Agentic Educational Content Generation for African Languages on Edge Devices
Ravi Gupta, Guneet Bhatia
TL;DR
<3-5 sentence high-level summary> Addresses educational inequity and multilingual content barriers in Sub-Saharan Africa by proposing an autonomous CrewAI framework that orchestrates four edge-optimized agents to generate culturally adaptive educational content. The approach combines Markov Decision Processes for curriculum planning, RLHF-tuned African language models (InkubaLM, Lugha-LLaMA, Nguni-XLMR) and on-device coordination to deliver efficient, multilingual content on Raspberry Pi 4B and Jetson Nano. Key results show InkubaLM achieving leading edge performance (Jetson Nano TTFT 129 ms, 45.2 t/s; Pi TTFT 326 ms, 15.9 t/s) with strong quality metrics (BLEU 0.688, cultural relevance 4.4/5, fluency 4.2/5). The work advances sustainable, off-grid education via solar-powered deployments and community governance, contributing to UN SDGs 4, 9, and 10 and offering a scalable model for localized AI-enabled learning.
Abstract
Addressing educational inequity in Sub-Saharan Africa, this research presents an autonomous agent-orchestrated framework for decentralized, culturally adaptive educational content generation on edge devices. The system leverages four specialized agents that work together to generate contextually appropriate educational content. Experimental validation on platforms including Raspberry Pi 4B and NVIDIA Jetson Nano demonstrates significant performance achievements. InkubaLM on Jetson Nano achieved a Time-To-First-Token (TTFT) of 129 ms, an average inter-token latency of 33 ms, and a throughput of 45.2 tokens per second while consuming 8.4 W. On Raspberry Pi 4B, InkubaLM also led with 326 ms TTFT and 15.9 tokens per second at 5.8 W power consumption. The framework consistently delivered high multilingual quality, averaging a BLEU score of 0.688, cultural relevance of 4.4/5, and fluency of 4.2/5 across tested African languages. Through potential partnerships with active community organizations including African Youth & Community Organization (AYCO) and Florida Africa Foundation, this research aims to establish a practical foundation for accessible, localized, and sustainable AI-driven education in resource-constrained environments. Keeping focus on long-term viability and cultural appropriateness, it contributes to United Nations SDGs 4, 9, and 10. Index Terms - Multi-Agent Systems, Edge AI Computing, Educational Technology, African Languages, Rural Education, Sustainable Development, UN SDG.